20th week of 2022 patent applcation highlights part 55 |
Patent application number | Title | Published |
20220156537 | METHOD OF GENERATING COLOR SAMPLE DATA, METHOD OF PREPARING COLOR SAMPLE, AND COLOR SAMPLE PREPARATION DEVICE - The method of generating color sample data includes the step of generating the color sample data for preparing a color sample of a color included in a difference area between a color gamut in an equipment independent color space which is expressed by a first color expression apparatus and a color gamut in the equipment independent color space which is expressed by a second color expression apparatus using an output profile which expresses the color and corresponds to one of the first color expression apparatus and the second color expression apparatus configured to express a color in at least a part of the difference area out of a first output profile representing a correspondence relationship between a coordinate value in an output color space depending on the first color expression apparatus and a coordinate value in the equipment independent color space, and a second output profile representing a correspondence relationship between a coordinate value in an output color space depending on the second color expression apparatus and a coordinate value in the equipment independent color space based on a coordinate value in the difference area. | 2022-05-19 |
20220156538 | NON-TRANSITORY COMPUTER READABLE STORAGE MEDIUM, INFORMATION PROCESSING DEVICE AND PRINTING METHOD - A printer is caused to perform duplex printing by an information processing device in which an OS standard printing program is installed. When causing a printer connected to a PC to execute duplex printing based on a print instruction output from an editing application installed in the PC, an auxiliary program that supports the printer executes rotation processing of rotating an image of a page, which is required to be rotated, by 180° for intermediate data received from a general-purpose print program, executes rearrangement processing of rearranging a processing order from a page order to a print order for print data received from the general-purpose print program, according to a sheet conveying aspect of the printer, and transmits the print data after the rotation processing and the rearrangement processing from the PC to the printer. | 2022-05-19 |
20220156539 | BITMAP PROCESSING OF DIGITAL DOCUMENTS - A bitmap processing system for creating digital documents on a digital printing press by a fulfiller includes a fulfiller operated raster image processor that receives customer application Page Description Language (PDL) job files containing information for creating the digital documents and generates bitmaps in accordance with the files and a fulfiller operated editor that modifies the bitmaps so that the resulting documents process more efficiently in production steps downstream of a printing process. | 2022-05-19 |
20220156540 | LONG RUNNING WORKFLOWS FOR DOCUMENT PROCESSING USING ROBOTIC PROCESS AUTOMATION - Systems and methods for executing a robotic process automation (RPA) workflow for document processing are provided. An input document is processed by a first robot executing one or more document processing activities of the RPA workflow. The document processing activities may include optical character recognition, digitization, classification, or data extraction. Execution of the RPA workflow is suspended by the first robot in response to a user validation activity of the RPA workflow. The user validation activity provides for user validation of the results of the one or more document processing activities. A user request that requests validation of the results from an end user is generated and the user request is transmitted to the end user. The execution of the RPA workflow is resumed by a second robot based on the validation received from the end user. | 2022-05-19 |
20220156541 | TRANSPONDERS AND SENSORS FOR IMPLANTABLE MEDICAL DEVICES AND METHODS OF USE THEREOF - Implantable transponders comprising no ferromagnetic parts for use in medical implants are disclosed herein. Such transponders may assist in preventing interference of transponders with medical imaging technologies. Such transponders may optionally be of a small size, and may assist in collecting and transmitting data and information regarding implanted medical devices. Methods of using such transponders, readers for detecting such transponders, and methods for using such readers are also described. | 2022-05-19 |
20220156542 | SMART CARD - A smart card includes a first circuit delivering a power supply voltage and a second circuit coupled to the first circuit by an electrical conductor and powered with the power supply voltage. A light-emitting diode has a first terminal coupled to the electrical conductor and a second terminal coupled to a first terminal of the second circuit. During a first operating phase, the first circuit delivers a first value of the power supply voltage and the second circuit applies a first voltage to the first terminal. During a second operating phase, the first circuit delivers a second value of the power supply voltage and the second circuit applies a second voltage to the first terminal. | 2022-05-19 |
20220156543 | MANAGEMENT METHOD OF TEST FIXTURES APPLIED TO TEST PROCEDURE - A management method of test fixtures applied to a test procedure comprises: binding electronic tags to the test fixtures respectively, obtaining pieces of data respectively stored in the electronic tags by a reader device, obtaining the pieces of data from the reader device and obtaining original usage counts respectively associated with the pieces of data from a storage device by a processing device, determining whether each of the original usage counts does not exceed a threshold by the processing device, performing the test procedure on an object under test using the test fixtures when each of the original usage counts does not exceed the threshold, and after performing the test procedure, generating updated usage counts according to the original usage counts and replacing the original usage counts in the storage device with the updated usage counts respectively by the processing device. | 2022-05-19 |
20220156544 | Key Fob - A key fob, comprising an electronic communication circuit, a processor, and a battery configured to power the electronic communication circuit and the processor, further comprises: a communication module for exchanging data with an external electronic communication device, an access control module for exchanging access control data with an external electronic access control device, and a user activatable operating element which activates the communication module, or the access control module, depending on actuation of the operating element by a user. | 2022-05-19 |
20220156545 | RFID BEAD LABEL DEVICES CAPABLE OF WITHSTANDING AND MAINTAINING RFID OPERABILITY FOR IDENTIFICATION PURPOSES DURING AND POST-VULCANIZATION OF RUBBER ARTICLES - Disclosed are pre-cure RFID-enabled bead labels based on an RFID inlay construction consisting of an aluminum antenna etched on to a high temperature resistant polyimide film that is connected to an integrated memory circuit positioned on the surface of the polyimide film. This RFID inlay being further inserted into an overall label construction having a plurality of layers that include, for example, a plurality of polyester layers and a plurality of high temperature resistant adhesive layers that bond/adhere layers together, the plurality of layers further protecting and insulating the RFID inlay while the label is bonded to the external bead (or sidewall) of a tire. The compositions/devices disclosed herein can be used for electronic identification when applied on rubber-based articles (e.g., tires) prior to being subjected to stress related to the vulcanization process and normal use of this article during the manufacturing process. | 2022-05-19 |
20220156546 | PORTABLE ELECTRONIC DEVICE, IC CARD AND PROGRAM - According to an embodiment, a portable electronic device that executes a command from a host device includes a sensor and a processor. The sensor acquires biometric information. The processor causes the sensor to acquire first biometric information for generating a template used for authentication, and after the first biometric information is acquired, causes the sensor to acquire second biometric information used for generating the template. Where the similarity between the first biometric information and the second biometric information exceeds a first threshold value, the processor outputs a signal indicating that the second biometric information is inappropriate for use as biometric information for generating the template. | 2022-05-19 |
20220156547 | SYSTEMS AND METHODS FOR COUNTING AND INSPECTING OBJECTS - A system for count separation of objects comprises a controller, cameras adapted to detect each individual object in a stream of falling objects such that the controller can count the objects, a first receiving location adapted to directly receive the stream of falling objects, a second receiving location adapted to receive objects diverted from the stream of falling objects or to receive the stream of falling objects when the stream of falling objects is diverted from the first receiving location; a mechanical diverter having (a) a first position to not divert the stream of falling objects from the first receiving location and (b) a second position in to divert the stream of falling objects to the second receiving location, and an air blast diverter adapted (a) to divert specific objects or the stream of falling objects to the second location. | 2022-05-19 |
20220156548 | System and Method for Improving a Processing System - A system and corresponding method improve a processing system. The system comprises a first learning system coupled to a system controller. The first learning system identifies variations for altering processing of a processing system to meet at least one goal. The system controller applies the variations identified to the processing system. The system further comprises a second learning system coupled to the system controller. The second learning system determines respective effects of the variations identified and applied. The first learning system converges on a given variation of the variations based on the respective effects determined. The given variation enables the at least one goal to be met, improving the processing system, such as by increasing throughput, reducing latency, reducing power consumption, reducing temperature, etc. | 2022-05-19 |
20220156549 | SEARCH AND MATCH OPERATIONS IN SPIKING NEURAL NETWORKS - The present disclosure is directed to search and match operations of a spiking neural network (SNN) that performs in-memory operations. To model a computer-implemented SNN after a biological neural network, the architecture in the present disclosure involves different memory sections for storing inbound spike messages, synaptic connection data, and synaptic connection parameters. The section of memory containing synaptic connection data to identify matching inbound spike messages. Various embodiments are directed to an efficient search and match operation performed in memory to determine targeted synaptic connections. | 2022-05-19 |
20220156550 | MEDIA CAPTURE DEVICE WITH POWER SAVING AND ENCRYPTION FEATURES FOR PARTITIONED NEURAL NETWORK - A method for power saving and encryption during analysis of media captured by an information capture device using a partitioned neural network includes replicating, by an information capture device, an artificial neural network (ANN) from a computer server to the information capture device. The ANN on the computer server and a replicated ANN, both, include M layers. The method further includes, in response to captured data being input to be processed, partially processing, by the information capture device, the captured data by executing a first k layers using the replicated ANN, wherein only the k layers are selected to execute on the information capture device. The method further includes transmitting, by the information capture device, an output of the k-th layer to the computer server, which partially processes the captured data by executing the remainder of the M layers using the ANN and the output of the k-th layer. | 2022-05-19 |
20220156551 | METHOD OF TRANSMITTING AND MERGING DATA - A method of transmitting and merging data is adapted to a sender and a receiver that are in communication with each other. The method comprises a sending stage and a receiving stage. The sending stage comprises: transmitting a first block data, a second block data and a third block data to the receiver by the sender; obtaining a fourth block data and a fifth block data by the sender; and transmitting the third, fourth and fifth block data to the receiver by the sender. The receiving stage comprises: receiving the first, second, and third block data by the receiver; merging the first, second and third block data to perform a convolution operation by the receiver; receiving the third, fourth and fifth block data by the sender; and merging the third, fourth and fifth block data to perform another convolution operation. | 2022-05-19 |
20220156552 | DATA CONVERSION LEARNING DEVICE, DATA CONVERSION DEVICE, METHOD, AND PROGRAM - Accurate conversion to data of a conversion target domain is allowed. A training unit | 2022-05-19 |
20220156553 | ATTENTION NEURAL NETWORKS WITH SPARSE ATTENTION MECHANISMS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing network inputs using an attention neural network that has one or more sparse attention sub-layers. Each sparse attention sub-layer is configured to apply a sparse attention mechanism that attends differently for input positions that are in a first proper subset of the input positions in the input to the sub-layer than for positions that are not in the first proper subset. | 2022-05-19 |
20220156554 | Lightweight Decompositional Convolution Neural Network - A neural network (NN) and corresponding method employ an NN element (NNE) that includes a depthwise convolutional layer (DCL). The DCL outputs respective features by performing spatial convolution of respective input features having an original number of dimensions. The NNE includes a compression-expansion (CE) module that includes a first convolutional layer (CL) and second CL. The first CL outputs respective features as a function of respective input features. The respective features output from the first CL have a reduced number of dimensions relative to the original number of dimensions. The second CL outputs respective features, having the original number of dimensions, as a function of the respective features output from the first CL. The NNE further includes an add operator that outputs respective features as a function of the respective features output from the second CL and DCL. The NNE enables the NN to have a reduced size and to process data with competitive performance relative to conventional lightweight deep neural networks. | 2022-05-19 |
20220156555 | HIERARCHICAL TIME-SERIES PREDICTION METHOD - A hierarchical time-series prediction method is adapted to a plurality of reconciled predictions of a plurality of nodes of a hierarchical structure. The plurality of nodes have a plurality of time-series respectively, the plurality of reconciled predictions correspond to the plurality of time-series, the plurality of nodes comprises a plurality of bottom nodes, and the hierarchical time-series prediction method comprises: generating a plurality of individual predictions corresponding to the plurality of time-series respectively by a plurality of predictive models; generating a plurality of bottom-level predictions corresponding to the plurality of bottom nodes according to the plurality of individual predictions and an encoder network; and generating the plurality of reconciled predictions according to the plurality of bottom-level predictions and a decoder associated with the hierarchical structure. | 2022-05-19 |
20220156556 | SPIKING NEURAL NETWORK CIRCUIT - Disclosed is a spiking neural network circuit, which includes an axon circuit that generates an input spike signal, a first synapse zone and a second synapse zone each including one or more synapses, wherein each of the synapses is configured to perform an operation based on the input spike signal and each weight, and a neuron circuit that generates an output spike signal based on operation results of the synapses. The input spike signal is transferred to the first synapse zone and the second synapse zone through a tree structure, and each of branch nodes of the tree structure includes a driving buffer. | 2022-05-19 |
20220156557 | SCHEDULING NEURAL NETWORK PROCESSING - A computer-implemented method includes receiving a batch of neural network inputs to be processed using a neural network on a hardware circuit. The neural network has multiple layers arranged in a directed graph and each layer has a respective set of parameters. The method includes determining a partitioning of the neural network layers into a sequence of superlayers. Each superlayer is a partition of the directed graph that includes one or more layers. The method includes processing the batch of inputs using the hardware circuit, which includes, for each superlayer in the sequence: i) loading the respective set of parameters for the layers in the superlayer into memory of the hardware circuit, and ii) for each input in the batch, processing the input through each of the layers in the superlayer using the parameters in the memory of the hardware circuit to generate a superlayer output for the input. | 2022-05-19 |
20220156558 | SUB-HOURLY LOAD DISAGGREGATION OF HOME APPLIANCES USING ELECTRIC SMART METER READS PROCESSED INSIDE SMART METERS - The present invention provides a method for determining probable presence, in a surveyed household, of appliances having no load sensors, said method implemented by one or more processing devices to perform:
| 2022-05-19 |
20220156559 | ARTIFICIAL NEURAL NETWORK BYPASS - Apparatuses and methods can be related to implementing bypass paths in an ANN. The bypass path can be used to bypass a portion of the ANN such that the ANN generates an output with a particular level of confidence while utilizing less resources than if the portion of the ANN had not been bypassed. | 2022-05-19 |
20220156560 | ARTIFICIAL NEURAL NETWORK BYPASS COMPILER - Apparatuses and methods can be related to compiling instructions for implementing an artificial neural network (ANN) bypass. The bypass path can be used to bypass a portion of the ANN such that the ANN generates an output with a particular level of confidence while utilizing less resources than if the portion of the ANN had not been bypassed. A compiler can determine where to place the bypass path in an ANN. | 2022-05-19 |
20220156561 | IDENTIFYING MICROORGANISMS USING THREE-DIMENSIONAL QUANTITATIVE PHASE IMAGING - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying the predicted type of one or more microorganisms. In one aspect, a system comprises a phase-contrast microscope and a microorganism classification system. The phase-contrast microscope is configured to generate a three-dimensional quantitative phase image of one or more microorganisms. The microorganism classification system is configured to process the three-dimensional quantitative phase image using a neural network to generate a neural network output characterizing the microorganisms, and thereafter identify the predicted type of the microorganisms using the neural network output. | 2022-05-19 |
20220156562 | NEURAL NETWORK OPERATION MODULE AND METHOD - A neural network operation module, which comprises a storage unit that stores output neurons, weight precision and output neuron gradient precision of a multi-layer neural network; a controller unit that obtains an average value Y1 of the absolute value of the output neuron before fixed-point and an average value Y2 of the absolute value of the output neuron after fixed-point; if Y1/Y2 is greater than a preset threshold K, obtaining the output neuron gradient precision of adjacent two layers of the multi-layer neural network, and obtaining an estimation value A | 2022-05-19 |
20220156563 | Detecting adversary attacks on a deep neural network (DNN) - A method, apparatus and computer program product to protect a deep neural network (DNN) having a plurality of layers including one or more intermediate layers. In this approach, a training data set is received. During training of the DNN using the received training data set, a representation of activations associated with an intermediate layer is recorded. For at least one or more of the representations, a separate classifier (model) is trained. The classifiers, collectively, are used to train an outlier detection model. Following training, the outliner detection model is used to detect an adversarial input on the deep neural network. The outlier detection model generates a prediction, and an indicator whether a given input is the adversarial input. According to a further aspect, an action is taken to protect a deployed system associated with the DNN in response to detection of the adversary input. | 2022-05-19 |
20220156564 | ROUTING SPIKE MESSAGES IN SPIKING NEURAL NETWORKS - The present disclosure is directed to routing of data in a spiking neural network (SNN) that performs in-memory operations. To model a computer-implemented SNN after a biological neural network, the architecture in the present disclosure involves different memory sections for storing inbound spike messages, synaptic connection data, and synaptic connection parameters. Embodiments are directed to routing spike messages through various router-based topologies. For example, spike messages may be multicasted to target routers using address tables. | 2022-05-19 |
20220156565 | NEUROMORPHIC CIRCUIT INCLUDING SPIKE REGULATOR BASED ON FLASH MEMORY - Embodiments of inventive concepts relate to a neuromorphic circuit including a flash memory-based spike regulator capable of generating a stable spike signal with a small number of devices. The neuromorphic circuit may generate a simple and stable spike signal using a flash memory-based spike regulator. Therefore, it is possible to implement a semiconductor neuromorphic circuit at low power and low cost by using the spike regulator of the present invention. Example embodiments of inventive concepts provide a neuromorphic circuit comprising a control signal generator for generating a control signal for generating a pulse signal; and a spike regulator for generating a spike signal in response to the control signal. Wherein the spike regulator comprises a first transistor for switching an input signal transmitted to one terminal to the other terminal in response to the control signal; and a first flash memory type transistor having a drain terminal connected to the other terminal of the first transistor and transferring the switched input signal to a source terminal as a spike signal. | 2022-05-19 |
20220156566 | STREAMING ACCELERATORS AND STREAMING SYSTEMS INCLUDING THE SAME - A streaming accelerator includes a first pool, a first switch bus, a second pool and a second switch bus. The first pool includes neural processing unit (NPU) bundles, and each of NPU bundles includes a plurality of NPUs. The first switch bus provides a first streaming data to a first selected NPU bundle and a second selected NPU bundle respectively. The second pool includes network interface card (NIC) bundles, and each of the NIC bundles includes an encoder and a NIC. The second switch bus provides a first intermediate streaming data and a second intermediate streaming data to a first selected NIC bundle and a second selected NIC bundle. The first selected NIC bundle encodes the first intermediate streaming data to generate a first encoded streaming data. The second selected NIC bundle encodes the second intermediate streaming data to generate a second encoded streaming data. | 2022-05-19 |
20220156567 | NEURAL NETWORK PROCESSING UNIT FOR HYBRID AND MIXED PRECISION COMPUTING - A neural network (NN) processing unit includes an operation circuit to perform tensor operations of a given layer of a neural network in one of a first number representation and a second number representation. The NN processing unit further includes a conversion circuit coupled to at least one of an input port and an output port of the operation circuit to convert between the first number representation and the second number representation. The first number representation is one of a fixed-point number representation and a floating-point number representation, and the second number representation is the other one of the fixed-point number representation and the floating-point number representation. | 2022-05-19 |
20220156568 | DUAL-SPARSE NEURAL PROCESSING UNIT WITH MULTI-DIMENSIONAL ROUTING OF NON-ZERO VALUES - A general matrix-matrix (GEMM) accelerator core includes first and second buffers, a control logic circuit, and a first processing element (PE). The first buffer receives a elements of a first matrix A of activation values. The second buffer receives b elements of a second matrix B of weight values. The control logic circuit replaces a zero-valued a element in a first column of the first buffer with a nonzero-valued a element that is within a maximum borrowing distance of a location of the zero-valued a element in the first column of the first buffer. The PE receives a elements from the first column of the first buffer including the nonzero-valued element a selected to replace the zero-valued a element and receives b elements from locations in the second buffer that correspond to locations in the first buffer from where the a elements have been received by the PE. | 2022-05-19 |
20220156569 | WEIGHT-SPARSE NEURAL PROCESSING UNIT WITH MULTI-DIMENSIONAL ROUTING OF NON-ZERO VALUES - A general matrix-matrix (GEMM) accelerator core includes first and second buffers, and a processing element (PE). The first buffer receives a elements of a matrix A of activation values. The second buffer receives b elements of a matrix B of weight values. The matrix B is preprocessed with a nonzero-valued b element replacing a zero-valued b element in a first row of the second buffer based on the zero-valued b element being in the first row of the second buffer. Metadata is generated that includes movement information of the nonzero-valued b element to replace the zero-valued b element. The PE receives b elements from a first row of the second buffer and a elements from the first buffer from locations in the first buffer that correspond to locations in the second buffer from where the b elements have been received by the PE as indicated by the metadata. | 2022-05-19 |
20220156570 | SINGLE-LAYERED LINEAR NEURAL NETWORK BASED ON CELL SYNAPSE STRUCTURE - A single-layered linear neural network based on a cell synapse structure comprising a pre-synapse and a post-synapse, the pre-synapse comprises a plurality of precursor resistors, number of the precursor resistors is m, one end of the precursor resistors in the pre-synapse is jointly connected with an intermediate point, and another end of the precursor resistors is respectively connected with each of a plurality of precursor signal input ends, number of the precursor signal input ends is m; the precursor signal input ends are used for receiving input voltages; the post-synapse comprises a plurality of posterior resistors, number of the precursor resistors is n, one end of the posterior resistors in the post-synapse is jointly connected with the intermediate point, and another end of the posterior resistors is respectively connected with each of a plurality of posterior signal output ends, number of the posterior signal output ends is n; the posterior signal output ends are used for outputting currents. The invention provides a single-layered linear neural network based on cell synapse structure, which can reduce the number of resistors; in addition, a weight between an external precursor neuron and an external posterior neuron can be changed only by adjusting two variable resistors or one of the two variable resistors. | 2022-05-19 |
20220156571 | OPTICAL CONVOLUTIONAL NEURAL NETWORK ACCELERATOR - An accelerator for modern convolutional neural networks applies the Winograd filtering algorithm in a wavelength division multiplexing integrated photonics circuit modulated by a memristor-based analog memory unit. | 2022-05-19 |
20220156572 | DATA PARTITIONING WITH NEURAL NETWORK - A computer-implemented method, system and computer program product for processing a data set is provided. In this method, an original data set including a plurality of data records is obtained. Each data record in the original data set has values of a first number of features. A representative data set having the plurality of representative data records is determined. Each representative data record has values of a second number of representatives. The second number of representatives are obtained by training an autoencoder neutral network with values of the first number of features as inputs, and the second number is smaller than the first number. The plurality of representative data records is segmented into two or more clusters based on the values of the second number of representatives. The representative data records in the two or more clusters are partitioned to form a predefined number of representative data subsets. | 2022-05-19 |
20220156573 | Machine Learning Engine Providing Trained Request Approval Decisions - Systems, devices, and methods for automated approval of claim requests for solicited procedures. In an embodiment, a system includes an audit manager and an attention-based neural network. A computer-readable memory stores tuning parameters and a set of risk level thresholds. A database is configured to store training data including fixed length and variable length data. Fixed length data includes features and a target label. Variable length data includes medical procedure code approval history data. Validation data and operation data may also be stored in the database. The audit manager is configured to output an approval indication and rejection probability score for each solicited procedure according to a selected risk level threshold in the set of risk level thresholds. In one feature, an attention-based neural network is trained according to features and target label in the fixed length data and medical procedure code approval history data in the variable length data. | 2022-05-19 |
20220156574 | METHODS AND SYSTEMS FOR REMOTE TRAINING OF A MACHINE LEARNING MODEL - A computer-implemented method for training a machine learning model, the method comprising performing, by a computing device, a plurality of training iterations, wherein each training iteration comprises inputting a set of training data to the machine learning model, determining an output of the model from processing the set of training data, and updating one or more parameters of the model based on the output of the model, the method further comprising, for one or more of the training iterations, determining, based on the output of the model for the training iteration, a measure of the stability of the model; and determining, based on the stability of the model, whether to send the updated model parameters via a communication channel to a remote computing device. | 2022-05-19 |
20220156575 | MULTI-DIMENSIONAL TENSOR SUPPORT EXTENSION IN NEURAL NETWORK PROCESSOR - Embodiments of the present disclosure relate to a tensor access operation circuit in a neural processor circuit. The neural processor circuit further includes a data processor circuit and at least one neural engine circuit. The tensor access operation circuit indirectly accesses at least a region of a source tensor in a system memory having a rank, and maps one or more source components of the source tensor into an input tensor having another rank. The data processor circuit stores an output version of the input tensor obtained from the tensor access operation circuit and sends the output version of the input tensor as multiple of units of input data to the at least one neural engine circuit. The at least one neural engine circuit performs at least convolution operations on the units of input data and at least one kernel to generate output data. | 2022-05-19 |
20220156576 | METHODS AND SYSTEMS FOR PREDICTING DYNAMIC OBJECT BEHAVIOR - Methods and systems for predicting behavior of a dynamic object of interest in an environment of a vehicle are described. Time series feature data are received, representing features of objects in the environment, including a dynamic object of interest. The feature data are categorized into one of a plurality of defined object categories. Each categorized set of data is encoded into a respective categorical representation that represents temporal change of features within the respective defined object category. The categorical representations are combined into a single shared representation. A categorical interaction representation is generated based on the single shared representation that represents contributions of temporal change in each defined object category to a final time step of the shared representation. The categorical interaction representation together with data representing dynamics of the objects in the environment and data representing a state of the vehicle are used to generate predicted data representing a predicted future behavior of the dynamic object of interest. | 2022-05-19 |
20220156577 | TRAINING NEURAL NETWORK MODEL BASED ON DATA POINT SELECTION - An electronic device includes a memory to store neural network model trained for classification tasks of real-time applications. The neural network model is trained with plurality of training data points. The electronic device includes circuitry to retrieve a plurality of external data points. The electronic device applies the neural network model on the plurality of external data points to determine a plurality of impact scores for each external data point. The plurality of impact scores indicates amount of contribution of each training data point towards a prediction of each external data point. The electronic device selects a set of external data points based on the plurality of impact scores. The electronic device updates the plurality of training data points with the set of external data points to generate a second plurality of training data points and re-trains the neural network model based on the second plurality of training data points. | 2022-05-19 |
20220156578 | STATISTICAL CONFIDENCE METRIC FOR RECONSTRUCTIVE ANOMALY DETECTION MODELS - Approaches herein relate to reconstructive models such as an autoencoder for anomaly detection. Herein are machine learning techniques that measure inference confidence based on reconstruction error trends. In an embodiment, a computer hosts a reconstructive model that encodes and decodes features. Based on that decoding, the following are automatically calculated: a respective reconstruction error of each feature, a respective moving average of reconstruction errors of each feature, an average of the moving averages of the reconstruction errors of all features, a standard deviation of the moving averages of the reconstruction errors of all features, and a confidence of decoding the features that is based on a ratio of the average of the moving averages of the reconstruction errors to the standard deviation of the moving averages of the reconstruction errors. The computer detects and indicates that a threshold exceeds the confidence of decoding, which may cause important automatic reactions herein. | 2022-05-19 |
20220156579 | METHOD AND DEVICE FOR SELECTING ANSWER TO MULTIPLE CHOICE QUESTION - The present disclosure relates to a method and device for generating an answer to a multiple-choice question, and an object of the present disclosure is to improve accuracy of answer generation by predicting an incorrect answer as well as a correct answer through a plurality of networks. In order to achieve the above object, the present disclosure provides a device for detecting an incorrect answer based on a text, a question, and a plurality of options corresponding to a multiple-choice question, including: a first network that predicts a correct answer by calculating a correct answer probability corresponding to each of the plurality of options, a second network that predicts an incorrect answer by calculating an incorrect answer probability corresponding to each of the plurality of options, and a third network that selects a final prediction based on the correct answer probability of the first network and the incorrect answer probability of the second network. | 2022-05-19 |
20220156580 | ANOMALY DETECTION DEVICE AND ANOMALY DETECTION METHOD BASED ON GENERATIVE ADVERSARIAL NETWORK ARCHITECTURE - An anomaly detection device based on a generative adversarial network architecture, which uses the single-type training data composed of multiple normal signals to train an anomaly detection model. The anomaly detection device includes an encoder, a generator, a discriminator, and a random vector generator. In the training phase of anomaly detection model, the random latent vectors generated by the random vector generator are sequentially input to a generator to generate the synthesized signals with the same dimension as the normal signals. The synthesized signals are sequentially input into a discriminator to output the corresponding discriminant values. When the corresponding discriminant values are under the predetermined threshold, the corresponding synthesized signals are selected as the anomalous class training data, and the real normal signals are selected as the normal class training data. | 2022-05-19 |
20220156581 | SYSTEMS AND METHODS FOR REINFORCED HYBRID ATTENTION FOR MOTION FORECASTING - Systems and methods for reinforced hybrid attention for motion forecasting are provided. According to one embodiment, a system for reinforced hybrid attention for motion forecasting is provided. The system includes a sensor module, a hard attention module, a soft attention module, and a motion module. The sensor module receives patio-temporal historical observations associated at least one element in an environment. The hard attention module selects information from the spatio-temporal historical observations associated with the at least one element based on a reinforcement learning model. The soft attention generates ranked information by applying attention weights to the selected information. The motion module generates motion predictions based on the ranked information. | 2022-05-19 |
20220156582 | Generating Knowledge Graphs From Conversational Data - Techniques for building knowledge graphs from conversational data are disclosed. The systems include a high-performance relation classifier developed with active learning and requiring minimal supervision. The classifier is used to classify relation triples extracted from conversational text, which are then used to populate the knowledge graph. A heuristic for constructing the knowledge graph is also disclosed. The proposed embodiments provide a way to efficiently build and/or augment knowledge graphs and improve the quality of the generated responses by a dialogue agent despite a sparsity of data. | 2022-05-19 |
20220156583 | METHOD OF GENERATING CLASSIFIER BY USING SMALL NUMBER OF LABELED IMAGES - A method of generating a classifier by using a small number of labeled images includes: pre-training a wide residual network by using a set of labeled data with a data amount meeting requirements, and determining portions of the pre-trained wide residual network except for a fully connected layer as a feature extractor for an image; randomly selecting, for a N-class classifier to be generated, N classes from a training set for each of a plurality of times; and for N classes selected each time: randomly selecting one or more images from each class of the N classes as training samples; extracting a feature vector from training samples of each class by using the feature extractor; inputting a total of N feature vectors extracted into a classifier generator; and sequentially performing a class information fusion and a parameter prediction for the N-class classifier by using the classifier generator. | 2022-05-19 |
20220156584 | METHOD AND APPARATUS FOR UPDATING A NEURAL NETWORK - Described herein is a method of generating a media bitstream to transmit parameters for updating a neural network implemented in a decoder, wherein the method includes the steps of: (a) determining at least one set of parameters for updating the neural network; (b) encoding the at least one set of parameters and media data to generate the media bitstream; and (c) transmitting the media bitstream to the decoder for updating the neural network with the at least one set of parameters. Described herein are further a method for updating a neural network implemented in a decoder, an apparatus for generating a media bitstream to transmit parameters for updating a neural network implemented in a decoder, an apparatus for updating a neural network implemented in a decoder and computer program products comprising a computer-readable storage medium with instructions adapted to cause the device to carry out said methods when executed by a device having processing capability. | 2022-05-19 |
20220156585 | TRAINING POINT CLOUD PROCESSING NEURAL NETWORKS USING PSEUDO-ELEMENT - BASED DATA AUGMENTATION - Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing training of a neural network that is configured to process a network input comprising a point cloud to generate a network output for a point cloud processing task. The system obtains a set of labeled training examples and a set of unlabeled point clouds, generates a respective pseudo-label for each unlabeled point cloud, generates a plurality of pseudo-elements based on the respective pseudo-label for the unlabeled point cloud, generates augmented training data by augmenting the labeled training examples using the pseudo-elements generated for the unlabeled point clouds, and performing training of the neural network on the augmented training data. | 2022-05-19 |
20220156586 | SYSTEM FOR MONITORING A CIRCUIT BREAKER - A system for monitoring a circuit breaker includes at least one sensor and a processor. The at least one sensor is configured to be located and utilized to obtain at least one time series sensor data of at least one first part an operational circuit breaker. The at least one sensor is configured to provide the at least one time series sensor data of the at least one first part of the operational circuit breaker to the processor. The processor is configured to determine that at least one second part of the operational circuit breaker is operating correctly or has a fault, where the determination includes analysis of the at least one time series sensor data of the at least one first part of the operational circuit breaker by a trained neural network implemented by the processor. | 2022-05-19 |
20220156587 | MULTI-HEAD DEEP METRIC MACHINE-LEARNING ARCHITECTURE - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a multi-head deep metric machine-learning architecture. The architecture is used to perform techniques that include obtaining multiple features that are derived from data values of an input dataset and identifying, for an input image of the input dataset, global features and local features among the features. The techniques also include determining a first set of vectors from the global features and a second set of vectors from the local features; computing, from the first and second sets of vectors, a concatenated feature set based on a proxy-based loss function and pairwise-based loss function. A feature representation that integrates the global features and the local features are generated based on the concatenated feature set. A machine-learning model is generated and configured to output a prediction about an image based on inferences derived using the feature representation. | 2022-05-19 |
20220156588 | KERNEL PREDICTION WITH KERNEL DICTIONARY IN IMAGE DENOISING - Certain embodiments involve techniques for efficiently estimating denoising kernels for generating denoised images. For instance, a neural network receives a noisy reference image to denoise. The neural network uses a kernel dictionary of base kernels and generates a coefficient vector for each pixel in the reference image such that the coefficient vector includes a coefficient value for each base kernel in the kernel dictionary, where the base kernels are combined to generate a denoising kernel and each coefficient value indicates a contribution of a given base kernel to a denoising kernel. The neural network calculates the denoising kernel for a given pixel by applying the coefficient vector for that pixel to the kernel dictionary. The neural network applies each denoising kernel to the respective pixel to generate a denoised output image. | 2022-05-19 |
20220156589 | Processing Sensor Data With Multi-Model System On Resource-Constrained Device - Methods, systems, and computer-readable media for multi-model processing on resource-constrained devices. A resource-constrained device can determine, based on a battery-life for a battery of the device, whether to process input through a first model or a second model. The first model can be a gating model that is more energy efficient to execute, and the second model can be a main model that is more accurate than the gating model. Depending on the current battery-life and/or other criteria, the system can process, through the gating model, sensor input that can record activity performed by a user of the resource-constrained device. If the gating model predicts an activity performed by the user that is recorded by the sensor data, the device can process the same or additional input through the main model. Overall power consumption can be reduced with a minimum accuracy maintained over processing input only through the main model. | 2022-05-19 |
20220156590 | ARTIFICIAL INTELLIGENCE SYSTEM AND ARTIFICIAL NEURAL NETWORK LEARNING METHOD THEREOF - Disclosed is a method for learning an artificial neural network in a synapse of an artificial intelligence system including generating, by an input neuron of the artificial intelligence system, a first input signal, generating, by the input neuron, a second input signal after a predetermined time, generating, by an output neuron of the artificial intelligence system, an output signal in response to the first input signal and the second input signal that are generated by the input neuron, and adjusting, by the synapse of the artificial intelligence system, connection strength of the artificial neural network based on a temporal order of the first input signal and the second input signal that are generated by the input neuron. | 2022-05-19 |
20220156591 | SYSTEMS AND METHODS FOR SEMI-SUPERVISED LEARNING WITH CONTRASTIVE GRAPH REGULARIZATION - Embodiments described herein provide an approach (referred to as “Co-training” mechanism throughout this disclosure) that jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings. Specifically, two representations of each image sample are generated: a class probability produced by the classification head and a low-dimensional embedding produced by the projection head. The classification head is trained using memory-smoothed pseudo-labels, where pseudo-labels are smoothed by aggregating information from nearby samples in the embedding space. The projection head is trained using contrastive learning on a pseudo-label graph, where samples with similar pseudo-labels are encouraged to have similar embeddings. | 2022-05-19 |
20220156592 | SYSTEMS AND METHODS FOR CONTRASTIVE ATTENTION-SUPERVISED TUNING - Embodiments described herein embodiments described herein provide Contrastive Attention-Supervised Tuning (CAST), a training method to fix the visual grounding ability of contrastive SSL methods based on a data augmentation strategy using unsupervised saliency maps. In addition to the contrastive loss that encourages the model to pick the crop that comes from the corresponding image, CAST provides an explicit grounding supervision through a Grad-CAM based attention loss that enforces models to look at the specified object of interest that is common across different crops when making this decision. A new geometric transform is introduced for randomly cropping different views from an input image based on certain constraints derived from a saliency map. | 2022-05-19 |
20220156593 | SYSTEMS AND METHODS FOR VIDEO REPRESENTATION LEARNING WITH A WEAK TEACHER - Embodiments described herein provide systems and methods for learning representation from unlabeled videos. Specifically, a method may comprise generating a set of strongly-augmented samples and a set of weakly-augmented samples from the unlabeled video samples; generating a set of predictive logits by inputting the set of strongly-augmented samples into a student model and a first teacher model; generating a set of artificial labels by inputting the set of weakly-augmented samples to a second teacher model that operates in parallel to the first teacher model, wherein the second teacher model shares one or more model parameters with the first teacher model; computing a loss objective based on the set of predictive logits and the set of artificial labels; updating student model parameters based on the loss objective via backpropagation; and updating the shared parameters for the first teacher model and the second teacher model based on the updated student model parameters. | 2022-05-19 |
20220156594 | FEATURE ENHANCEMENT VIA UNSUPERVISED LEARNING OF EXTERNAL KNOWLEDGE EMBEDDING - A method, computer system, and computer program product for enhancing feature engineering based on unsupervised learning of associated external knowledge embedding are provided. The embodiment may include receiving, by a processor, input data as a table and a name of a column. The embodiment may also include analyzing the column to identify multisets of concepts or sequences of concepts. The embodiment may further include automatically expanding the column by linking the identified multisets or the sequences of the concepts with corresponding concepts in an external knowledge graph. The embodiment may also include training a neural network to learn embedding vectors of concept multi-sets in the expanded column of the tables, wherein the training is unsupervised without provision of labels of data when the neural network learns an embedding of the multisets of concepts with an objective to minimize a reconstruction error of the identified multisets of concepts. | 2022-05-19 |
20220156595 | SYSTEM AND METHOD FOR SUPERVISED LEARNING OF PERMEABILITY OF EARTH FORMATIONS - Embodiments herein include a method for characterizing a rock formation sample. The method for characterizing a rock formation sample includes obtaining a plurality of data sets characterizing the rock formation sample. The method further includes training a neural network to generate a computational model. Moreover, the method additionally includes using the plurality of data sets as input to the computational model, wherein the computational model may be implemented by a processor that derives an estimate of permeability of the rock formation sample. | 2022-05-19 |
20220156596 | NEURAL ARCHITECTURE SEARCH METHOD BASED ON KNOWLEDGE DISTILLATION - Provided is a neural architecture search method based on knowledge distillation, which trains a student network using knowledge acquired from a teacher network and searches a target neural network. The neural architecture search method may include the steps of: (a) extracting an image feature map from a learning model of the student network; (b) calculating a loss function by comparing an image feature map extracted from a learning model of the teacher network to the image feature map extracted in the step (a); (c) selecting a block whose capacity is to be increased and a block whose capacity is to be decreased, for each learning model block of the student network, based on the loss function; and (d) deciding a candidate learning model of the student network according to the block architecture selected in the step (c). | 2022-05-19 |
20220156597 | Automatic Processing of Electronic Files to Identify Genetic Variants - A mechanism is provided for processing electronic files to identify genetic variants of a gene. Evidence of one or more genetic variants of the gene and corresponding information is extracted from a corpus of information. Each genetic variant of the one or more genetic variants is classified based on whether the genetic variant is identified as being pathogenic. Genetic variant annotation is then performed to generate a summary. | 2022-05-19 |
20220156598 | INTERACTIVE SEMANTIC DATA EXPLORATION FOR ERROR DISCOVERY - Classification predictions made by a concept classifier may be interactively visualized and explored in a user interface that displays visual representations of a plurality of data items in a star coordinate space spanned by a plurality of anchor concepts each mapping the data items onto respective finite real-valued scores. Positions of the visual representations of the data items in the star coordinate space are based on the scores for the plurality of anchor concepts, and may be updated responsive to a user manipulating the anchor concepts in the user interface, e.g., by moving or modifying definitions of anchor concepts, or by adding or deleting anchor concepts. The visual representations may of the data items may reflect labels and/or classification predictions, and may be updated based on updated classification predictions following retraining the of the concept classifier based on added training data or new features. | 2022-05-19 |
20220156599 | GENERATING HYPOTHESIS CANDIDATES ASSOCIATED WITH AN INCOMPLETE KNOWLEDGE GRAPH - A hypothesis generation system may determine sets of link types that are respectively associated with a plurality of nodes included in an incomplete knowledge graph to determine a plurality of intersection-over-union scores. The hypothesis generation system may determine, based on a plurality of vectors of an embedding space representation associated with the incomplete knowledge graph, a plurality of similarity scores and may determine, based on the plurality of intersection-over-union scores and the plurality of similarity scores, a plurality of affinity scores. The hypothesis generation system may determine, based on the plurality of affinity scores and the plurality of nodes, one or more node pairs; may generate, for a node pair, of the one or more node pairs, one or more triplet hypothesis candidate templates; and may generate, for a triplet hypothesis candidate template, of the one or more triplet hypothesis candidate templates, a plurality of triplet hypothesis candidates. | 2022-05-19 |
20220156600 | USING GRAPH PATTERNS TO AUGMENT INTEGRATION OF MODELS INTO A SEMANTIC FRAMEWORK - Provided is a computer system including at least one processor for modeling operations related to capturing domain knowledge. The operations include creating, via the processor, a graph model of inputs to an equation relevant to the domain knowledge. The graph model relates at least one of the inputs to another one of the inputs; and wherein the graph model relates the inputs to an output. The operations also include deriving augmented-type information from the graph model and adding, via the processor, the derived augmented-type information to the equation, the adding facilitating use of the equation by artificial intelligence. | 2022-05-19 |
20220156601 | Cognitive Personas - A method, system and computer-usable medium for performing cognitive computing operations comprising receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching for incorporation into a cognitive graph; defining a cognitive persona within the cognitive graph, the cognitive persona corresponding to an archetype user model, the cognitive persona comprising a set of nodes in the cognitive graph; associating a user with the cognitive persona; and, performing a cognitive computing operation based upon the cognitive persona associated with the user. | 2022-05-19 |
20220156602 | PREDICTION RULE CALIBRATION SYSTEM AND PREDICTION RULE CALIBRATION METHOD - In classification problems or regression problems, a prediction rule that is highly accurate, simple, and in match with the knowledge of experts is obtained. A system includes a prediction rule simplification unit that simplifies a prediction rule of a learning model using an evaluation metric and a restriction; a branch condition search unit that updates a part of the simplified branch condition for prediction rule based on calibration information expressing a request for a prediction value or a specific branch condition; and a threshold optimization unit that updates a part of a threshold of the simplified prediction rule based on the calibration information. | 2022-05-19 |
20220156603 | DISCOVERING FARMING PRACTICES - One embodiment provides a method, including: training a machine-learning model to produce customized farming practices specific to a farm to increase crop yield; wherein the training includes obtaining, from remote sensed data, (i) information corresponding to a crop of each of a plurality of farms and (ii) information corresponding to farming practices of each of the plurality of farms; wherein the training further includes detecting, from the remote sensed data, geographical features and farming characteristics of each of the plurality of farms; wherein the machine-learning model identifies from relationships between (iii) crop information and farming practices and (iv) geographical features and farming characteristics; and discovering, for a specific farm in an identified geographical location, utilizing the trained machine-learning model, and from farm-specific remote-sensed data, farming practices. | 2022-05-19 |
20220156604 | IDENTIFICATION OF COMPARTMENTS IN GAS RESERVOIRS - Disclosed are methods, systems, and computer-readable medium to perform operations including generating a material balance plot for a plurality of wells in a gas reservoir. The material balance plot includes, for each of the plurality of wells, respective static pressure/compressibility factor (P/Z) values plotted against cumulative production in the gas reservoir. The operations further include calculating, for each of the plurality of wells, a respective slope of the respective P/Z values plotted against cumulative production. Also, the operations include grouping, based on the respective slopes and locations of the plurality of wells, each well into a respective cluster. Additionally, the operations include designating each respective cluster as a separate compartment in the gas reservoir. | 2022-05-19 |
20220156605 | SYSTEM FOR EXTENDING FUNCTIONALITY OF HYPOTHESES GENERATED BY SYMBOLIC/LOGIC-BASED REASONING SYSTEMS - A vehicle and a system and a method of operating the vehicle. The system includes a reasoning engine, an episodic memory, a resolver and a controller. The reasoning engine infers a plurality of possible scenarios based on a current state of an environment of the vehicle. The episodic memory determines a historical likelihood for each of the plurality of possible scenarios. The resolver selects a scenario from the plurality of possible scenarios using the historical likelihoods. The controller operates the vehicle based on the selected scenario. | 2022-05-19 |
20220156606 | IDENTIFICATION OF A SECTION OF BODILY TISSUE FOR PATHOLOGY TESTS - Embodiments are provided for identification of a section of bodily tissue as either a candidate or a non-candidate for pathology tests. In some embodiments, a system can include a processor that executes computer-executable components stored in memory. The computer-executable components can include a feature composition component that generates a feature vector representing a physical model describing dye dynamics that determines a group of multispectral images of a section of bodily tissue. The computer-executable components also can include a classification component that generates a classification attribute for the section of bodily tissue by applying a classification model to the feature vector. The classification attribute designates the section of bodily tissue as one of biopsy-candidate or non-biopsy-candidate. | 2022-05-19 |
20220156607 | SYSTEM AND METHOD FOR TRAINING RECOMMENDATION POLICIES - Session-based Recommendation (SR) is the task of recommending the next item based on previously recorded user interactions. However, most existing approaches for SR either rely on costly online interactions with real users (model-free approaches) or rely on potentially biased rule-based or data-driven user-behavior models (model-based approaches) for learning. This disclosure relates to a system and method for selecting session-based recommendation policies using historical recommendations and user feedback. Herein, the learning of recommendation policies given offline or batch data from old recommendation policies based on a Distributional Reinforcement Learning (DRL) based recommender system in the offline or batch-constrained setting without requiring access to a user-behavior model or real-interactions with the users. | 2022-05-19 |
20220156608 | INFERENCE DEVICE, INFERENCE METHOD, AND RECORDING MEDIUM - An inference device makes an inference in accordance with first-order predicate logic by using: a true or false of a proposition that determines a state of a target by using a predicate that represents the state of the target; and an inference rule where a predicate representing a state of a target in an antecedent differs from a predicate representing a state of a target in a consequent. The predicate representing the state of the target in the antecedent and the predicate representing the state of the target in the consequent represent a proposition that determines a state of a target in a different time step. | 2022-05-19 |
20220156609 | METHOD AND SYSTEM FOR PROCESSING MULTI-REQUEST APPLICATIONS - A system receives application data to be used in requests made on behalf of an applicant to a selection of evaluator devices. The system includes a predictive model which predicts actual eligibility criteria for acceptance of a request by the evaluator devices, and is trained with a library of application data including previously evaluated requests and outcomes to the previously evaluated requests. The system compiles the application data into separate requests by synchronizing the application data and identifying a common core of data required by each selected evaluator device and compiling the common core of data along with particular requirements of individual evaluator devices. An applicant can thereby complete a multi-request application which generates requests to a plurality of evaluator devices and which avoids duplication of data storage and data transmission, and reduces effort required by the applicant. Implementations include students making applications for admission to academic institutions | 2022-05-19 |
20220156610 | HORTICULTURE GROWING SYSTEM WITH CONTROL SYSTEM WITH OPTIMIZED PARAMETERS DRIVEN BY CLOUD BASED MACHINE LEARNING - A horticulture growing system where a growing regimen is prescribed to achieve desired growing results. The system has self-learning mechanisms where the prescribed growing regimens are continually optimized to achieve the desired results through machine learning and deep learning. The system uses both a cloud based dynamic system model for growing and a local grow model. Various techniques are utilized to improve data collection and labeling. The results (the system's ability to accurately create growing regimens which produce the desired grow objectives) are improved using the dynamic system model and the local grow model. The models are trained and adjusted using datasets from multiple growing operations to increase the efficacy of the self-learning mechanisms. This system may also include a mechanism for in-harvest re-optimization to improve grow results in real-time. | 2022-05-19 |
20220156611 | METHOD AND APPARATUS FOR ENTERING INFORMATION, ELECTRONIC DEVICE, COMPUTER READABLE STORAGE MEDIUM - A method and apparatus for entering information are provided. The method includes: clustering acquired to-be-identified materials to obtain a question-and-answer material; performing corpus-processing on the question-and-answer material to obtain a question-and-answer corpus pair, the question-and-answer corpus pair comprising at least one question and an answer to each question of the at least one question; performing title determination on the question-and-answer corpus pair to obtain at least one title and an answer corresponding to each title of the at least one title; and storing the at least one title and an answer corresponding to each title of the at least one title in a question bank in a structured manner. | 2022-05-19 |
20220156612 | LEARNING LATENT STRUCTURAL RELATIONS WITH SEGMENTATION VARIATIONAL AUTOENCODERS - Learning disentangled representations is an important topic in machine learning for a wide range of applications. Disentangled latent variables represent interpretable semantic information and reflect separate factors of variation in data. Although generative models may learn latent representations and generate data samples as well, existing models may ignore the structural information among latent representations. Described in the present disclosure are embodiments to learn disentangled latent structural representations from data using decomposable variational auto-encoders, which simultaneously learn component representation and encodes component relationships. Embodiments of a novel structural prior for latent representations are disclosed to capture interactions among different data components. Embodiments are applied to data segmentation and latent relation discovery among different data components. Experiments on several datasets demonstrate the utility of the present model embodiments. | 2022-05-19 |
20220156613 | METHOD AND SYSTEM FOR GENERATING A SOCIO-TECHNICAL DECISON IN RESPONSE TO AN EVENT - A method includes receiving, by a processing circuit, a plurality of solutions to avoid or decrease an adverse effect caused by an event. The method also includes selecting, by the processing circuit, a selected solution from the plurality of solutions by performing a socio-technical decision process. The socio-technical decision process includes simulating a human decision using a behavior model and a goal model for each of a plurality of agents and simulating a system decision using a sequential error search method for each of a plurality of systems. The socio-technical decision process also includes generating a socio-technical decision using the human decisions and the system decisions. The socio-technical decision corresponds to the selected solution. The method further includes facilitating a performance of one or more actions to implement the socio-technical decision. | 2022-05-19 |
20220156614 | BEHAVIORAL PREDICTION AND BOUNDARY SETTINGS, CONTROL AND SAFETY ASSURANCE OF ML & AI SYSTEMS - Typical autonomous systems implement black-box models for tasks such as motion detection and triaging failure events, and as a result are unable to provide an explanation for its input features. An explainable framework may utilize one or more explainable white-box architectures. Explainable models allow for a new set of capabilities in industrial, commercial, and non-commercial applications, such as behavioral prediction and boundary settings, and therefore may provide additional safety mechanisms to be a part of the control loop of automated machinery, apparatus, and systems. An embodiment may provide a practical solution for the safe operation of automated machinery and systems based on the anticipation and prediction of consequences. The ability to guarantee a safe mode of operation in an autonomous system which may include machinery and robots which interact with human beings is a major unresolved problem which may be solved by an exemplary explainable framework. | 2022-05-19 |
20220156615 | SYSTEM, APPARATUS, AND METHOD TO IDENTIFY INTELLIGENCE USING A DATA PROCESSING PLATFORM - A system and method includes: implementing an intelligence and insights service; identifying an anomalous observation output by a data processing pipeline based on streams of data sourced from a subscriber to the intelligence and insights service; recursively inputting into a subset of the data processing pipeline of the intelligence and insights service a plurality of dimensions of the streams of data based on attributes of the anomalous observation; automatically identifying one or more driving factors causing the output of the anomalous observation based on an analysis within the subset of the data processing pipeline of plurality of dimensions of the streams of data; generating a story component based on a conversion of the one or more driving factors; and augmenting the story component to a pre-existing story relating to the anomalous observation that is provided to the subscriber via a user interface. | 2022-05-19 |
20220156616 | NODE SHARING FOR A RULE ENGINE CODED IN A COMPILED LANGUAGE - Aspects and features of the present disclosure can reconcile node sharing within a production rule network that is fully coded in a compiled language. As an example, the shared, stateless class can represent constraints shared by the alpha node of a rete network. Code can be post processed to create a shared stateless class defined in memory. When the rule engine is executed and the rule network is produced, the shared stateless class can be referenced to evaluate a constraint shared by a node of the production rule network, reducing the number of classes stored in memory. Garbage collection can be used within the shared stateless class, deleting objects from memory structure when no longer used, further improving storage efficiency. | 2022-05-19 |
20220156617 | MULTI-DIMENSIONAL AIRCRAFT COLLISION CONFLICT RISK EVALUATION SYSTEM - A multi-dimensional aircraft collision risk evaluation system in the field of collision prediction for civil aviation aircraft is disclosed. The system calculates probabilities of overlapping between an aircraft and one or more other aircraft in three dimensions; calculates loss interval rates of the aircraft in three dimensions; obtains probabilities of collision between the aircraft in directions corresponding to the three dimensions; compares the probabilities of collision in the three dimensions of the aircraft to obtain a maximum probability and a dimension corresponding to the maximum probability; and calculates a difference value between the maximum probability and a safety standard, and making or giving a safety evaluation according to the difference value. Accordingly, the calculation of the multi-dimensional aircraft collision risk probability is realized. The maximum collision risk probability is calculated, and a determination criterion for a comprehensive safety evaluation of the aircraft is provided based on the maximum collision risk probability. | 2022-05-19 |
20220156618 | ENSEMBLE CLASSIFICATION ALGORITHMS HAVING SUBCLASS RESOLUTION - Ensemble classification algorithms having subclass resolution are disclosed. An example disclosed apparatus includes a fingerprint generator to generate a fingerprint of class probabilities of each of a plurality of samples, a distribution creator to create a distribution of the samples based on the generated fingerprints, and a distribution applicator to apply the distribution to a population to predict sub-class probabilities of each of the population. | 2022-05-19 |
20220156619 | Optically Multiplexed Quantum Control Interface - A qubit control system for a quantum computer includes an optical waveguide configured to receive and transmit therethrough a wavelength division multiplexed optical signal which has a plurality of modulated optical carriers, each optical carrier being at a different optical wavelength and carrying a digital qubit control signal; an optical demultiplexer optically coupled to the optical waveguide to receive the multiplexed optical signal to recover the plurality of modulated optical carriers; a plurality of photodetectors in communication with the optical demultiplexer; a plurality of cryogenic filters in communication with the plurality of photodetectors, each being configured to filter corresponding one of the plurality of digital qubit control signals to provide a corresponding one of a plurality of analog qubit control signals which is directed to a corresponding superconducting qubit and the photodetectors. The cryogenic filters are provided at a cryogenic temperature. | 2022-05-19 |
20220156620 | DETERMINISTIC RESET OF SUPERCONDUCTING QUBIT AND CAVITY MODES WITH A MICROWAVE PHOTON COUNTER - The disclosed technology is directed to systems and methods for deterministic reset of superconducting qubit and cavity modes with a microwave photon counter. The system comprises a multiplicity of qubit-microwave photon counter pairs coupled by a qubit-qubit coupling. Each of the qubit-microwave photon counter pairs comprise a qubit circuit, a microwave photon counter circuit, and a resonant cavity coupling the qubit circuit and the microwave photon counter circuit. | 2022-05-19 |
20220156621 | FAULT-TOLERANT QUANTUM HARDWARE USING HYBRID ACOUSTIC-ELECTRICAL QUBITS - A fault tolerant quantum computer is implemented using hybrid acoustic-electric qubits. A control circuit includes an asymmetrically threaded superconducting quantum interference devices (ATS) that excites excite phonons in a mechanical resonator by driving a storage mode of the mechanical resonator and dissipates phonons from the mechanical resonator via an open transmission line coupled to the control circuit, wherein the open transmission line is configured to absorb photons from a dump mode of the control circuit. | 2022-05-19 |
20220156622 | HIGH-FIDELITY MEASUREMENT OF BOSONIC MODES - High-fidelity measurements of qubits are achieved by increasing a number of measurements taken by use of a swap operation and a readout qubit, deflating a bosonic qubit for which measurement outcomes are affected by single photon/phonon loss events, deflating a bosonic qubit enabling readout in other basis, and evolving the qubit under a Hamiltonian that couples a mode to be measured to another mode where the Hamiltonian is selected from a three wave mixing interaction, and/or a combination of these techniques. | 2022-05-19 |
20220156623 | System and Method of Exchanging Information Through a Wireless Brain-Computer Interface - A system used to implement the method of exchanging information through a wireless brain-computer interface includes a specified brain and a quantum supercomputer. The quantum supercomputer is initially used to detect a plurality of compositional particles within the specified brain. A quantum entanglement is then induced in between each compositional particle and the quantum supercomputer. The quantum supercomputer is subsequently used to generate an eigenmatrix of the specified brain with the quantum supercomputer, wherein the eigenmatrix is a representation of each compositional particle. The method concludes by enabling two-way communication between the specified brain and the quantum supercomputer by modifying the eigenmatrix. | 2022-05-19 |
20220156624 | HYBRID-CYCLE QUANTUM-CLOCK FREQUENCY REGULATION - An atomic clock employs hybrid long/short quantum clock frequency regulation wherein each of a series of regulation cycles includes a relatively long (four Ramsey-cycle) combination error signal (CES) cycle and plural relatively short (two Ramsey-cycle) single error signal (SES) cycles. The CES cycles provide for better long-term stability than can be provided using only SES cycles. However, including the SES cycles between CES cycles improves short term stability with negligible diminishment of long-term stability. | 2022-05-19 |
20220156625 | METHOD AND SYSTEM FOR MULTIPLEXING SIGNALS - An entangled quantum system can be generated using entanglement-generating circuits that operate non-deterministically. Multiple instances of the entanglement generating circuit can be operated and outputs of successful instances can be propagated. The circuit can be implemented such that a photon that is part of the final output state passes through as few as one or two active switches from generation to the final output state. | 2022-05-19 |
20220156626 | QUBIT GATE AND PRODUCING A GENERALIZED CONTROLLED-NOT QUANTUM GATE - Preparing a metrologically-relevant entangled state includes: providing a plurality of atoms in a regular lattice, wherein each atom is in an initial quantum state of a first state in a ground state manifold; initializing a central atom in the regular lattice to a (|0 | 2022-05-19 |
20220156627 | SOFTWARE-DEFINED QUANTUM COMPUTER - The disclosure describes various aspects of a software-defined quantum computer. For example, a software-defined quantum computing architecture for allocating qubits is described that includes an application programming interface (API); a quantum operating system (OS) on which the API executes, with the quantum OS including a resource manager and a switch; and a plurality of quantum cores connected by the switch of the quantum resource OS. Moreover, the resource manager of the quantum resource OS determines an allocation of a plurality of qubits in the plurality of quantum cores. | 2022-05-19 |
20220156628 | SOFTWARE-DEFINED QUANTUM COMPUTER - The disclosure describes various aspects of a software-defined quantum computer. For example, a method is described for generating an intermediate representation of source code for a software-defined quantum computer. The method includes performing a lexical analysis on a high-level intermediate representation of a quantum programming language; performing semantic analysis on an output of the lexical analysis; and generating a mid-level intermediate representation of the quantum programming language based on an output of the semantic analysis. | 2022-05-19 |
20220156629 | CONTROL OF CHARGE CARRIERS IN QUANTUM INFORMATION PROCESSING ARCHITECTURES - Methods are disclosed for controlling charge stability in a device for quantum information processing. According to examples, a device for quantum information processing comprises a first plurality of confinement regions confining spinful charge carriers for use as audits. The device further comprises a second plurality of confinement regions confining spinful charge carriers, each confinement region of the second plurality of confinement regions adjacent to a confinement region of the first plurality of confinement regions. The device further comprises one or more charge reservoirs, wherein each confinement region of the second plurality of confinement regions is attachable to a charge reservoir. According to examples, a method for controlling charge stability comprises selectively tuning the relative energy levels of the first plurality of confinement regions and adjacent confinement regions of the second plurality of confinement regions such that, if a spinful charge carrier leaks from a confinement region of the first plurality of confinement regions, then the spinful charge carrier is replaced to ensure that the confinement region of the first plurality of confinement regions again contains a spinful charge carrier for use as a audit. Control apparatus and computer-readable media are also described herein. | 2022-05-19 |
20220156630 | TECHNOLOGIES FOR RESOURCE-EFFICIENT QUANTUM ERROR CORRECTION - Technologies for resource-efficient quantum error correction are disclosed. A quantum computer may include physical gate qubits, capable of general quantum gate operations such as single-qubit operations and nearest-neighbor two-qubit operations. Each physical qubit gate may be controllably coupled to a quantum memory. The quantum memory may have a lower per-gate error rate than the physical qubit gates as well as a lower per-qubit cost. Because errors accrue at a lower rate in the quantum memory, the physical gate qubits may be able to perform error correction for a large number of logical qubits in the quantum memory, even if the physical gate qubits have an error rate relatively close to an error threshold. | 2022-05-19 |
20220156631 | MACHINE-LEARNING MODEL TO PREDICT PROBABILITY OF SUCCESS OF AN OPERATOR IN A PAAS CLOUD ENVIORNMENT - Systems and methods are provided that integrate a machine-learning model, and more specifically, utilizing a platform as a service (PaaS) cloud to predict probability of success for an operator in an environment. An embodiment comprises a system having: a processor that executes computer executable components stored in memory, trained machine-learning model that predicts probability of success for deployment of an operator in an environment with a namespace of a platform as a service (PaaS) cloud, and a deployment component that receives a first operator and a first namespace and employs the trained machine-learning model to predict success of deployment of the first operator in a first environment. | 2022-05-19 |
20220156632 | IDENTIFYING GENETIC SEQUENCE EXPRESSION PROFILES ACCORDING TO CLASSIFICATION FEATURE SETS - Classifying genetic sequences by receiving genetic sequence data according to sequence features associated with gene expression, determining a genetic sequence feature set, determining a first classification for the genetic sequence feature set according to a machine learning model, defining a causal feature set associated with the first classification for the genetic sequence according to the machine learning model, altering the causal feature set for the genetic sequence, yielding an altered causal feature set, determining a second classification for the altered causal feature set according to the machine learning model, wherein the second classification differs from the first classification, and defining a set of target features, wherein the target features include causal features the altered causal feature set. | 2022-05-19 |
20220156633 | SYSTEM AND METHOD FOR ADAPTIVE COMPRESSION IN FEDERATED LEARNING - A computer-implemented method for training a machine learning model in a distributed system, the distributed system comprising a plurality of nodes that exchange updates to communally train the machine learning model. The method comprises a node: receiving an update to a local model from one or more other nodes in the distributed system, the local model being a locally maintained version of the machine learning model and the update specifying a change to one or more parameters of the local model; updating the local model based on the received update to determine an updated local model; determining for each parameter in the local model a change in the parameter relative to a previous version of the local model; and sending an update to the one or more other nodes in the distributed system, wherein the update includes an update to each parameter that has a change greater than a threshold. | 2022-05-19 |
20220156634 | Training Data Augmentation for Machine Learning - Techniques are disclosed relating to training a machine learning model to understand one or more rules without explicitly executing the rule. In some embodiments, a computer system generates synthetic samples for a trained machine learning model usable to make a classification decision, where the synthetic samples are generated from a rule and a set of existing samples. In some embodiments, the set of existing samples are selected based on exceeding a confidence threshold for the classification decision. In some embodiments, the computer system retrains the trained machine learning model using the synthetic samples. | 2022-05-19 |
20220156635 | Machine Learning Prediction For Recruiting Posting - The present disclosure provides systems and methods for predicting a date and time to post job advertisements using a prediction model generated by a machine learning algorithm such that candidates are more likely to view the job posting. The prediction model is trained using a machine learning algorithm based on a first split of a plurality of post records for job postings and view records corresponding to the first split of the post records. The post records include a post date, a post time, a country indicator, and a segment indicator for each of the job postings. The view records including a view date and a view time for each of the plurality of job postings. The predictions may be provided via an API. | 2022-05-19 |
20220156636 | EFFICIENT FLOOD WATERS ANALYSIS FROM SPATIO-TEMPORAL DATA FUSION AND STATISTICS - In an approach for efficient flood water analysis from spatio-temporal data fusion and statistics, a processor classifies regular waters by using cartographic data in a first location. A processor generates a water stream network including a watershed based on elevation data. A processor performs statistical analysis of spectral information from a multi-spectral satellite imagery over water bodies including the regular waters and flood waters. A processor correlates the spectral statistics of the multi-spectral satellite imagery to kinetic energy of the flood waters using machine learning techniques and physical modeling. A processor builds a learning model based on the correlation between the spectral statistics and the flood waters with the kinetic energy. A processor estimates kinetic energy of flood waters in a second location using the learning model. A processor evaluates a flooding risk for the second location based on the estimated flood waters kinetic energy. | 2022-05-19 |