19th week of 2019 patent applcation highlights part 59 |
Patent application number | Title | Published |
20190138838 | IMAGE PROCESSING METHOD AND PROCESSING DEVICE - There are provided an image processing method and an image processing device. The image processing method comprises: acquiring an input image; acquiring a first noise image and a second noise image; executing image conversion processing on the input image with the first noise image using a generative neural network, to acquire a first output image; and executing high resolution conversion processing on the first output image with the second noise image using a super-resolution neural network, to acquire a second output image, wherein the first noise image is different from the second noise image. | 2019-05-09 |
20190138839 | IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND PROGRAM - An image processing apparatus includes an image acquisition unit and a determination unit. The image acquisition unit uses a camera to acquire a first image representing an area in a first relative position and a second image representing an area in a second relative position closer to the moving direction of the vehicle than the first relative position. The determination unit compares the first image with the second image acquired earlier than the first image and representing an area overlapping the first image for luminance and/or the intensity of a predetermined color component to determine whether there exists a specific area higher in luminance than the surroundings or lower in luminance than the surroundings in the first image. | 2019-05-09 |
20190138840 | AUTOMATIC RULER DETECTION - In some implementations, a method includes: receiving, from the camera, a sample image that includes a fingerprint and a mensuration reference device, where the sample image is associated with a resolution; identifying (i) a plurality of edge candidate groups within the sample image, and (ii) a set of regularity characteristics associated with each of the plurality of edge candidate groups; determining that the associated set of regularity characteristics indicates the mensuration reference device; identifying a ruler candidate group, from each of the plurality of edge candidate groups, based at least on determining that the associated set of regularity characteristics indicates the mensuration reference device; computing a scale associated with the sample image based at least on extracting a set of ruler marks from the identified ruler candidate group; and generating, based at least on the scale associated with the sample image, a scaled image. | 2019-05-09 |
20190138841 | Wearable Device Capable of Recognizing Human Face and License Plate - A wearable device capable of recognizing a human face and a license plate includes a camera, an image capturing unit, a database, a central processing unit and a display unit. The camera receives external light to generate an image, and the image is captured by the image capturing unit. The captured image is transmitted to the central processing unit and recognized whether the image includes human faces or license plate of a car. The recognized data of human faces or license plate are compared with pre-stored data of human faces and license plate in the data base. When the recognized data matches the pre-stored data, the recognized data is shown in the display unit. | 2019-05-09 |
20190138842 | Method of Recognizing Human Face and License Plate Utilizing Wearable Device - A method for recognizing a human face and a license plate includes the following steps: providing a wearable device comprising an image capturing device; capturing an image through the image capturing device; determining whether a human face or a license plate is in the image; analyzing the human face or the license plate and generating recognized human face data or recognized license plate data when a human face or a license plate is in the image; comparing the recognized human face data or the recognized license plate data with a plurality of human face data and a plurality of license plate data saved in a database; and displaying the recognized human face data or the recognized license plate data when the recognized human face data or the recognized license plate data matches the human face data or the license plate data. | 2019-05-09 |
20190138843 | PHOTO SUBSCRIPTION SYSTEM AND METHOD USING BIOMETRIC IDENTIFICATION - A computer system and method for photo subscription using biometric identification is provided. A photo match request is received that identifies a subscriber of a plurality of subscribers and that selects one or more biometric signatures of at least one biometric signatures associated with the identified subscriber. Photo biometric data associated with one or more photographs inputted by at least one photo provider system is accessed. At least one biometric signature selected by the photo match request is accessed. A score is generated for each of the photos, directed to each selected biometric signature, which is based on a level of probability that the photo biometric data associated with the photo is a match for the selected biometric signature. The identification of a photo having a score of at least a first predetermined number is then outputted to the at least one selected destination. The photo biometric data for each photo having a score for a selected biometric signature of at least a second predetermined number is added to the selected biometric signature. | 2019-05-09 |
20190138844 | USING IMAGES AND IMAGE METADATA TO LOCATE RESOURCES - A method of using images and image metadata to locate one or more resources includes receiving a requests, each request requesting a location of a resource and including an image related to the resource, information specifying how the image and the resource are related, and metadata for the image. A queue is created for each of a plurality of responding systems, the queue ranked, and specifying the order in which the requests are to be displayed at respective responding systems. The generated queues and sent to their respective responding systems, and a response is received that specifies the location of a resource. | 2019-05-09 |
20190138845 | Detection Method and Device Thereof - This invention provides a detection method and a device thereof which are applied to the field of image processing. The method includes: receiving an image of a target object, acquiring a type of the target object according to a first classifier and the image of the target object, and sending information containing the type of the target object to a display device. The method can automatically prompt a product type, thereby reducing the time of manual recognition and increasing the accuracy of the recognition. | 2019-05-09 |
20190138846 | A METHOD FOR DETERMINING THE TEMPORAL PROGRESSION OF A BIOLOGICAL PHENOMENON AND ASSOCIATED METHODS AND DEVICES - Provided herein is a method for determining the temporal progression of a biological phenomenon which may affect a studied subject, the method including the steps of providing first data relative to biomarkers for the studied subject, the biomarkers being relative to the progression of the biological phenomenon, providing a numerical model, converting the first data into at least one point on the same Riemann manifold, and using a numerical model to determine a temporal progression for the biological phenomenon for the studied subject, the numerical model being a function in a Riemann manifold, the numerical model associating to values of biomarkers a temporal progression trajectory for the biological phenomenon and data relative to the dispersion of the progression trajectory for the biological phenomenon among a plurality of subjects, the numerical model being obtained by using a stochastic approximation in an expectation-maximization technique on data relative to biomarkers. | 2019-05-09 |
20190138847 | Computing Systems with Modularized Infrastructure for Training Generative Adversarial Networks - Example aspects of the present disclosure are directed to computing systems that provide a modularized infrastructure for training Generative Adversarial Networks (GANs). For example, the modularized infrastructure can include a lightweight library designed to make it easy to train and evaluate GANs. A user can interact with and/or build upon the modularized infrastructure to easily train GANs. According to one aspect of the present disclosure, the modularized infrastructure can include a number of distinct sets of code that handle various stages of and operations within the GAN training process. The sets of code can be modular. That is, the sets of code can be designed to exist independently yet be easily and intuitively combinable. Thus, the user can employ some or all of the sets of code or can replace a certain set of code with a set of custom-code while still generating a workable combination. | 2019-05-09 |
20190138848 | REALISTIC SENSOR SIMULATION AND PROBABILISTIC MEASUREMENT CORRECTION - Systems, apparatuses and methods may provide for technology that obtains a neural network output, which estimates a difference between a first measured output of a sensor and a simulated output of the sensor. The technology may also add the difference to the simulated output of the sensor. In one example, the neural network output includes mean displacement data and parametrically controllable covariance data. Additionally, the technology may subtract a point-wise difference from a second measurement output of the sensor. | 2019-05-09 |
20190138849 | ROTATION VARIANT OBJECT DETECTION IN DEEP LEARNING - System and method for detecting objects in geospatial images, 3D point clouds and Digital Surface Models (DSMs). Deep Convolution Neural Networks (DCNNs) are trained using positive and negative training examples. Using a rotation pattern match of only positive examples reduces the number of negative examples required. In DCNNs softmax probability is variant of rotation angles. When rotation angle is coincident with object orientation, softmax probability has maximum value. During training, positive examples are rotated so that their orientation angles are zero. During detection, test images are rotated through different angles. At each angle, softmax probability is computed. A final object detection is based on maximum softmax probability as well as a pattern match between softmax probability patterns of all positive examples and the softmax probability pattern of a target object at different rotation angles. The object orientation is determined at the rotation angle when softmax probability has maximum value. | 2019-05-09 |
20190138850 | WEAKLY-SUPERVISED SPATIAL CONTEXT NETWORKS - Systems, methods and articles of manufacture for training a convolutional neural network for feature recognition within digital images. A spatial context neural network is trained using a plurality of patches cropped from a plurality of digital images, the spatial context neural network comprising a first convolutional neural network configured to predict a feature representation for a first specified portion of a first digital image, a second convolutional neural network configured to compute a feature representation for a second specified portion of a second digital image, and a spatial context module that accepts output of the first and second convolutional neural networks as input. The second convolutional neural network is refined by regressing features of the second convolutional neural network to features of the first convolutional neural network. The refined second convolutional neural network is used to recognize one or more features within a third digital image. | 2019-05-09 |
20190138851 | NEURAL NETWORK-BASED IMAGE MANIPULATION - An image creation and editing tool can use the data produced from training a neural network to add stylized representations of an object to an image. An object classification will correspond to an object representation, and pixel values for the object representation can be added to, or blended with, the pixel values of an image in order to add a visualization of a type of object to the image. Such an approach can be used to add stylized representations of objects to existing images or create new images based on those representations. The visualizations can be used to create patterns and textures as well, as may be used to paint or fill various regions of an image. Such patterns can enable regions to be filled where image data has been deleted, such as to remove an undesired object, in a way that appears natural for the contents of the image. | 2019-05-09 |
20190138852 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM FOR GENERATING TEACHER INFORMATION - An information processing apparatus performs estimation processing on supervised data, and stores a relationship between teacher information and an estimation result. When unsupervised data is input, the information processing apparatus searches for supervised data high in degree of similarity in estimation result to unsupervised data, and generates teacher information from an estimation result of unsupervised data based on a relationship between teacher information and an estimation result about the detected supervised data. | 2019-05-09 |
20190138853 | SYSTEMS AND METHODS FOR ROBUST INDUSTRIAL OPTICAL CHARACTER RECOGNITION - An auto-encoder is configured to verify character detection and/or classification results generated by an automated optical character recognition system. The auto-encoder may be trained to reconstruct visual representations of the detected character, and a determination of whether the character detection result comprises a true positive or false positive may be based on a reconstruction error between the image data in which the character was detected and a reconstructed image generated by the auto-encoder. | 2019-05-09 |
20190138854 | METHOD AND APPARATUS FOR TRAINING FACE RECOGNITION MODEL - A method and apparatus for removing black eyepits and sunglasses in first actual scenario data having an image containing a face acquired from an actual scenario, to obtain second actual scenario data; counting a proportion of wearing glasses in the second actual scenario data; dividing original training data composed of an image containing a face into wearing-glasses and not-wearing-glasses first and second training data, where a proportion of wearing glasses in the original training data is lower than a proportion in the second actual scenario data; generating wearing-glasses third training data based on glasses data and the second training data; generating fourth training data in which a proportion of wearing glasses is equal to the proportion of wearing glasses in the second actual scenario data, based on the third training data and the original training data; and training a face recognition model based on the fourth training data. | 2019-05-09 |
20190138855 | VIDEO REPRESENTATION OF FIRST-PERSON VIDEOS FOR ACTIVITY RECOGNITION WITHOUT LABELS - A computer-implemented method, system, and computer program product are provided for activity recognition in a surveillance system. The method includes receiving a plurality of unlabeled videos from one or more cameras. The method also includes classifying an activity in each of the plurality of unlabeled videos. The method additionally includes controlling an operation of a processor-based machine to react in accordance with the activity. | 2019-05-09 |
20190138856 | INDUCTION SYSTEM FOR CROWD MONITORING - A system for monitoring an area includes a processor and an electromagnetic radiation source in communication with the processor. The electromagnetic radiation source is configured to emit radiation to heat a metallic object that is in or carried by a target. The system also includes an array of temperature sensors in communication with the processor, where the array of temperature sensors is configured to detect a first temperature associated with the target and a second temperature associated with the target. The first temperature is detected prior to emission of the radiation and the second temperature is detected subsequent to emission of the radiation. The processor is also configured to determine whether to trigger an alert based at least in part on a difference between the first temperature and the second temperature. | 2019-05-09 |
20190138857 | IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD AND RECORDING MEDIUM - In the image processing device, the image processing method and the recording medium, the image analyzer carries out image analysis on an image. The tag information assignor assigns the image with tag information corresponding to objects present in the image based on the result of the image analysis. The first assignment ratio calculator calculates an assignment ratio of common tag information assigned to images owned by users as the first assignment ratio. The second assignment ratio calculator calculates an assignment ratio of the common tag information assigned to images owned by each user as the second assignment ratio. And the tag ranking determiner ranks the common tag information assigned to images owned by the user based on the difference between the first assignment ratio and the second assignment ratio of the common tag information. | 2019-05-09 |
20190138858 | FILLING DEVICE - A method for preventing a malfunction of a filling device when a container is filled by a user with a beverage. The method includes providing a filling device comprising a control unit which controls the filling device, a camera which takes an image of a container currently being used with the filling device and which outputs the image to a classifier which then uses a trained learning algorithm to analyze the output of the image of the container provided by the camera. The trained learning algorithm of the classifier analyzes which container is currently being used based on characteristics of the container so as to classify the container into a predefined class. The predefined class is then employed by the control unit to prevent the malfunction of the filling device. | 2019-05-09 |
20190138859 | Display Control System And Recording Medium - There is provided a display control system including a plurality of display units, an imaging unit configured to capture a subject, a predictor configured to predict an action of the subject according to a captured image captured by the imaging unit, a guide image generator configured to generate a guide image that guides the subject according to a prediction result from the predictor, and a display controller configured to, on the basis of the prediction result from the predictor, select a display unit capable of displaying an image at a position corresponding to the subject from the plurality of display units, and to control the selected display unit to display the guide image at the position corresponding to the subject. | 2019-05-09 |
20190138860 | FONT RECOGNITION USING ADVERSARIAL NEURAL NETWORK TRAINING - The present disclosure relates to a font recognition system that employs a multi-task learning framework and adversarial training to improve font classification and remove negative side effects caused by intra-class variances of glyph content. For example, in one or more embodiments, the font recognition system adversarial trains a font recognition neural network by minimizing font classification loss while at the same time maximizing glyph classification loss. By employing an adversarially trained font classification neural network, the font recognition system can improve overall font recognition by removing the negative side effects from diverse glyph content. | 2019-05-09 |
20190138861 | System for Automated Decoration - A system for automated decoration of an item comprising the steps of: installing print generating software on a computer with a memory (e.g. a server); linking an input system (e.g. a web site) to the computer; allowing a customer to select an item (customer selection), preferably a fabric item, via the input system; allowing the customer to specify a decoration (customer specification) for the item via the input system; generating a print image for the item from the customer selection and specification with the print generating software; and sending the print image from the computer to a printer, which is preferably a dye sublimation printer. | 2019-05-09 |
20190138862 | MINIMIZING VISUAL VARIATIONS IN MULTI-LANE PRINT OUTPUTS - In an example, an apparatus is described that includes a vision system and an image correction module. The vision system captures an image of a multi-lane print output. The image correction module receives the image of the multi-lane print output from the vision system and calculates a calibration to image data from which the multi-lane output is printed. The calibration minimizes visual variations between the multi-lane print output and a reference image. | 2019-05-09 |
20190138863 | IMAGE FORMING APPARATUS AND RECORDING MEDIUM SUITABLE FOR IMAGE FORMING PROCESSING BASED ON PDL (PAGE DESCRIPTION LANGUAGE) - Provided is an image forming apparatus for further speeding up an image forming process. A first rendering core of a rendering core module executes data analysis of an object of PDL format printing information. A second rendering core executes a speculative process for generating a Display List for an object. A third rendering core executes a rendering process for a printout or display output based on the Display List generated by the second rendering core. In addition, data analysis by the first rendering core and the speculative process by the second rendering core are executed in parallel processing. As a result, the second rendering core can execute the generation of a Display List by a speculative process even without receiving a rendering command from the first rendering core. | 2019-05-09 |
20190138864 | SMART LABEL OR TAG HAVING A CONTINUITY SENSOR ON A SUBSTRATE HAVING A PREFERENTIAL TEARING DIRECTION AND SYSTEM INCLUDING THE SAME - A smart label including a communication device and a continuity sensor, and methods of manufacturing and using the same, are disclosed. The smart label includes a substrate having a preferential tearing direction, an antenna or display, an integrated circuit, and a sensing line configured to sense or determine a continuity state of a container on which the communication device is placed or to which the communication device is fixed or adhered. The sensing line has at least one section oriented perpendicularly or substantially perpendicularly to the preferential tearing direction of the substrate. The antenna is configured to receive a first wireless signal and/or transmit or broadcast a second wireless signal. The communication device (or integrated circuit) may further include a receiver and/or transmitter, in which case the integrated circuit may be configured to process the first wireless signal and/or information therefrom and/or generate the second wireless signal and/or information therefor. Alternatively, the smart label may include a display (and optionally a battery) instead of the antenna. The display may be configured to display the continuity state of the container. | 2019-05-09 |
20190138865 | MARKING APPARATUS AND MARKING SYSTEM - In accordance with an embodiment, a marking apparatus comprises an acquiring section configured to acquire first information associated with an object; a setting section configured to set parameters of a laser beam based on the first information; and a marking section configured to irradiate the object with the laser beam based on the parameters set by the setting section to mark second information on the object. | 2019-05-09 |
20190138866 | MACHINE-READABLE CODE - Technology for generating, reading, and using machine-readable codes is disclosed. There is a method, performed by an image capture device, for reading and using the codes. The method includes obtaining an image, identifying an area in the image having a machine-readable code. The method also includes, within the image area, finding a predefined start marker defining a start point and a predefined stop marker defining a stop point, an axis being defined there between. A plurality of axis points can be defined along the axis. For each axis point, a first distance within the image area to a mark is determined. The distance can be measured from the axis point in a first direction which is orthogonal to the axis. The first distances can be converted to a binary code using Gray code such that each first distance encodes at least one bit of data in the code. | 2019-05-09 |
20190138867 | AUTHENTICATION METHOD OF A TWO DIMENSIONAL BAR CODE - A method of producing a 2D barcode on an article including a laser markable layer, wherein the 2D barcode includes a primary information pattern representing primary information, which can be read by a 2D-barcode-reader, and a secondary information pattern embedded within the 2D barcode, which is difficult to reproduce without alteration, includes a laser marking step of exposing the laser markable layer with an infrared laser thereby forming the secondary information pattern of the 2D barcode. | 2019-05-09 |
20190138868 | Dual code authentication process - A dual code authentication process combining a visible QR code with an invisible randomly generated code which can be alpha, numeric, symbol or image that can only be read with a reading device. A data generation engine is used to create the generated code which is assigned to the QR code and stored in a cloud based database. The QR code is decodable by a handheld reading device which communicates with the cloud based database releasing a copy of the generated code to the reading device. A reader is then used to decode the invisible printed code wherein the user can compare the printed code on the document and the code stored on the cloud based database to determine a match and authenticity. | 2019-05-09 |
20190138869 | POWER ACTIVATION VIA CONDUCTIVE CONTACT LABEL - Various mechanisms for implementing power activation of electronic tags via conductive contact labels are provided herein. An electronic shipping tag includes a housing to enclose: a printed circuit board having: a battery; load circuitry; and a plurality of pins that project from the housing, such that when contacted with a conductive substrate, cause activation of the load circuitry. | 2019-05-09 |
20190138870 | TRACKING SYSTEM - A tracking system comprising a tag reader comprising an interrogating antenna. One or more tags comprising an electrical energy generator configured to convert environmental energy to electrical energy. A radio frequency, RF, communication circuit. A controller configured to use the electrical energy generated by the electrical energy generator to transmit a data signal to the tag reader using the RF communication circuit. | 2019-05-09 |
20190138871 | RFID TAG MANUFACTURING APPARATUS AND METHOD FOR MANUFACTURING RFID TAG - An RFID tag manufacturing apparatus that includes an antenna base material conveying part that conveys an antenna base material with antenna patterns in a first direction. Moreover, the apparatus includes a conveying part for an RFIC element that supplies an RFIC element having terminal electrodes for connection with the antenna patterns on one principal surface. A plotter is further provided that conveys the supplied RFIC element to a predetermined position of the antenna patterns and temporarily bonds the RFIC element to the antenna patterns. Finally, the apparatus includes a pressurizing part that applies a pressure to the temporarily bonded RFIC element to permanently bond the RFIC element to the antenna patterns. In an aspect, the plotter includes a fixed arm portion and a movable suction head. | 2019-05-09 |
20190138872 | TRANSACTION CARD HAVING STRUCTURAL REINFORCEMENT - The disclosed embodiments generally relate to transaction cards and methods for manufacturing transaction cards. The transaction card may include a first card component having a first surface and a first structural feature associated with the first surface. The transaction card may also include a second card component separate from the first card component and attachable thereto. The second card component may include a second surface and a second structural feature associated with the second surface. The first and second structural features may be configured to interconnect. | 2019-05-09 |
20190138873 | WIRELESS COMMUNICATION DEVICE, METHOD FOR MANUFACTURING SAME, SEAL FITTED WITH RFIC ELEMENT, AND METHOD FOR PRODUCING SAME - In a wireless communication device, radiation conductors including a first and second end portions are reformed on an upper surface of a radiation conductor base material. First and second terminal electrodes are provided at a same or substantially the same interval as the first and second end portions, on a lower surface of a RFIC element. A seal includes an adhesive surface larger than a principal surface of the RFIC element. The RFIC element is arranged on the upper surface of the radiation conductor substrate so that each of the first and second terminal electrodes comes into contact with the first and second end portions. The seal is pasted to the radiation conductor substrate so as to cover the RFIC element. | 2019-05-09 |
20190138874 | RFID-BASED INDICATOR FOR USE WITH FASTENING SUBSTRATES AND RELATED METHODS - An RFID apparatus for securing an object includes a security indication means having a breakable portion and an RFID transponder connected to the security indication means. The RFID transponder has at least one antenna, a collection of transistors, at least one conductive loop, and at least one RFID chip in electrical communication with a write-once circuit. At least a portion of the at least one conductive loop is positioned within the breakable portion of the security indication means. Breaking the at least one conductive loop causes the write-once circuit to change a signal state of the at least one RFID chip. | 2019-05-09 |
20190138875 | ELECTRONIC BADGE TO AUTHENTICATE AND TRACK INDUSTRIAL VEHICLE OPERATOR - A system for controlling an industrial vehicle comprises an information linking device, a badge communicator, an operator badge, and a controller. The controller controls the industrial vehicle operating state by identifying that an operator possessing the operator badge has approached the industrial vehicle, communicating with the server via the information linking device to authenticate the operator as authorized to operate the industrial vehicle, and pairing the operator badge with the industrial vehicle upon determining that the operator is authorized to operate the industrial vehicle. Moreover, the controller controls the industrial vehicle operating state by controlling the industrial vehicle based upon a location of the operator badge relative to the industrial vehicle. | 2019-05-09 |
20190138876 | IC TAG AND METHOD OF MANUFACTURING IC TAG - An IC tag is provided that reduces the size of a folded dipole antenna. The IC tag includes an IC chip and an antenna electrically connected with the IC chip. The antenna has a first linear portion, bent portions at both ends of the first linear portion, and second linear portions extending from the bent portions on both ends of the first linear portion, distal ends of the second-straight line portions face each other. Bent space portions are at both sides of space defined by the bent portions on both ends of the first linear portion, the first linear portion, and the second linear portions. A communication enhancer that tunes a resonant frequency to a desired frequency is provided near the distal ends of the second linear portions and provided at least inside or outside of space extending from one bent space portion to the other bent space portion. | 2019-05-09 |
20190138877 | TWO-DIMENSIONAL CODE INFORMATION QUERY METHOD, SERVER, CLIENT, AND SYSTEM - A two-dimensional code query method includes receiving a two-dimensional code query request from a first client, the two-dimensional code query request containing a first two-dimensional code, obtaining at least one two-dimensional codes that are bound to the first two-dimensional code, and returning the obtained two-dimensional codes to the first client for the first client to extract information from at least one of the obtained two-dimensional codes with a corresponding application on the first client. | 2019-05-09 |
20190138878 | NEURAL NETWORK ARCHITECTURES FOR SCORING AND VISUALIZING BIOLOGICAL SEQUENCE VARIATIONS USING MOLECULAR PHENOTYPE, AND SYSTEMS AND METHODS THEREFOR - Systems and methods for scoring and visualizing the effects of variants in biological sequences. Variants may include substitutions, insertions and deletions. The method comprises encoding biological sequences as vector sequences and then operating a neural network in the forward-propagation mode and possibly in the back-propagation mode to compute variant scores. Variant scores are determined by normalizing the gradients. Variant scores may be used to select a subset of variants, which are then used to produce modified vector sequences which are analyzed by the neural network operating in forward-propagation mode, to determine improved variant scores. The variant scores may be visualized using black and white, greyscale or colored elements that are arranged in blocks with dimensions corresponding to different possible symbols and the length of the sequence. These blocks are aligned with the biological sequence, which is illustrated by a symbol sequence arranged in a line. | 2019-05-09 |
20190138879 | BOT BUILDER DIALOG MAP - This disclosure relates to tools to facilitate the configuration of interactive agents, sometimes referred to as bots, chatbots, virtual robots, or talkbots. Specifically, the disclosure relates to the provision of a map view visualization of an interactive agent. The map view can display a complexity indicator or usage percentage for each dialog and provide an easy mechanism for creation of new dialogs, actions, parameters, rules, and logic. | 2019-05-09 |
20190138880 | WORKSPACE ACTOR SELECTION SYSTEMS AND METHODS - In one embodiment a method comprises: accessing information associated with a first actor, including sensed activity information associated with an activity space; analyzing the activity information, including analyzing activity of the first actor with respect to a plurality of other actors; and forwarding feedback on the results of the analysis, wherein the results includes identification of a second actor as a replacement actor to replace the first actor, wherein the second actor is one of the plurality of other actors. The activity space can include an activity space associated with performance of a task. The analyzing can comprise: comparing information associated with activity of the first actor within the activity space with anticipated activity of the respective ones of the plurality of the actors within the activity space; and analyzing/comparing deviations between the activity of the first actor and the anticipated activity of the second actor. | 2019-05-09 |
20190138881 | NEUROMORPHIC COMPUTING SYSTEM AND CURRENT ESTIMATION METHOD USING THE SAME - A neuromorphic computing system includes a synapse array, a switching circuit, a sensing circuit and a processing circuit. The synapse array includes row lines, column lines and synapses. The processing circuit is coupled to the switching circuit and the sensing circuit and is configured to connect a particular column line in the column lines to the first terminal by using the switching circuit, obtain a first voltage value from the particular column line by using the sensing circuit when the particular line is connected to the first terminal, connect the particular column line to the second terminal by using the switching circuit, obtain a second voltage value from the particular column line by using the sensing circuit when the particular line is connected to the second terminal, and estimate a sum-of-product sensing value according to a voltage difference between the first voltage value and the second voltage value. | 2019-05-09 |
20190138882 | METHOD AND APPARATUS FOR LEARNING LOW-PRECISION NEURAL NETWORK THAT COMBINES WEIGHT QUANTIZATION AND ACTIVATION QUANTIZATION - A method is provided. The method includes selecting a neural network model, wherein the neural network model includes a plurality of layers, and wherein each of the plurality of layers includes weights and activations; modifying the neural network model by inserting a plurality of quantization layers within the neural network model; associating a cost function with the modified neural network model, wherein the cost function includes a first coefficient corresponding to a first regularization term, and wherein an initial value of the first coefficient is pre-defined; and training the modified neural network model to generate quantized weights for a layer by increasing the first coefficient until all weights are quantized and the first coefficient satisfies a pre-defined threshold, further including optimizing a weight scaling factor for the quantized weights and an activation scaling factor for quantized activations, and wherein the quantized weights are quantized using the optimized weight scaling factor. | 2019-05-09 |
20190138883 | TRANSFORM FOR A NEUROSYNAPTIC CORE CIRCUIT - Embodiments of the present invention provide a method for feature extraction comprising generating synaptic connectivity information for a neurosynaptic core circuit. The core circuit comprises one or more electronic neurons, one or more electronic axons, and an interconnect fabric including a plurality of synapse devices for interconnecting the neurons with the axons. The method further comprises initializing the interconnect fabric based on the synaptic connectivity information generated, and extracting a set of features from input received via the electronic axons. The set of features extracted comprises a set of features with reduced correlation. | 2019-05-09 |
20190138884 | CONVERSION OF DIGITAL SIGNALS INTO SPIKING ANALOG SIGNALS - A digital signal may be converted into a spiking analog signal. A different constant current may be applied to each of a plurality of switch circuits. Each bit of the digital signal may be applied to a corresponding one of the plurality of switch circuits. Each switch circuit may apply the corresponding constant current to a common output when the corresponding bit has a predetermined value. Each switch circuit may not apply the corresponding constant current to the common output when the corresponding bit does not have the predetermined value. A common current may be applied at the common output to a spiking neuron circuit. | 2019-05-09 |
20190138885 | NEURAL RESPONSE HUMAN DETECTOR - Aspects provide human detector devices based on neuronal response, wherein the devices are configured to obtain electroencephalogram signals from an entity during a presentation of first sensory information to the entity, and compares the obtained electroencephalogram signals to each of a plurality of trained electroencephalogram signal profile portions that are labeled as the first sensory information that represent electroencephalogram signals most commonly generated by different persons as a function of presentation to the persons of sensory information corresponding to the first sensory information. Thus, the configured processor determines whether the entity is a human as a function of a strength of match of the obtained electroencephalogram signals to ones of the trained electroencephalogram signal profile portions labeled as first sensory information that have highest most-common weightings. | 2019-05-09 |
20190138886 | SYSTEM STATE PREDICTION - A method which includes steps of providing a state space model of behaviour of a physical system, the model including covariances for state transition and measurement errors, providing a data based regression model for prediction of state variables of the physical system, observing a state vector comprising state variables of the physical system, determining a prediction vector of state variables based on the state vector, using the regression model, and combining information from the state space model with predictions from the regression model through a Bayesian filter, is provided. | 2019-05-09 |
20190138887 | SYSTEMS, METHODS, AND MEDIA FOR GATED RECURRENT NEURAL NETWORKS WITH REDUCED PARAMETER GATING SIGNALS AND/OR MEMORY-CELL UNITS - Methods, systems and media for gated recurrent neural networks (RNNs) with reduced parameter gating signals and/or memory cell units are disclosed. In some embodiments, methods for analyzing sequential data are provided, the methods comprising: providing training data to an RNN including a first gate and gating signal; calculating an array of first parameters in a first equation used to calculate values of the first gating signal, including two or fewer parameters corresponding to arrays of values; receiving input data including first data and second data, the second data comes after the first data in a sequence; providing first data to the RNN; calculating a first gating signal; generating a first output; providing second data as input to the RNN; generating a second output; and providing a third output identifying one or more characteristics of the input data based on the first output and the second output. | 2019-05-09 |
20190138888 | WEIGHTED CASCADING CONVOLUTIONAL NEURAL NETWORKS - A cascading convolutional neural network (CCNN) comprising a plurality of convolutional neural networks (CNNs) that are trained by weighting training data based on loss values of each training datum between CNNs of the CCN. The CCNN can receiving an input image from plurality of images, classify the input image using the CCNN, and present a classification of the input image. | 2019-05-09 |
20190138889 | MULTI-FRAME VIDEO INTERPOLATION USING OPTICAL FLOW - Video interpolation is used to predict one or more intermediate frames at timesteps defined between two consecutive frames. A first neural network model approximates optical flow data defining motion between the two consecutive frames. A second neural network model refines the optical flow data and predicts visibility maps for each timestep. The two consecutive frames are warped according to the refined optical flow data for each timestep to produce pairs of warped frames for each timestep. The second neural network model then fuses the pair of warped frames based on the visibility maps to produce the intermediate frame for each timestep. Artifacts caused by motion boundaries and occlusions are reduced in the predicted intermediate frames. | 2019-05-09 |
20190138890 | EXPANDABLE AND REAL-TIME RECOFIGURABLE HARDWARE FOR NEURAL NETWORKS AND LOGIC REASONING - This invention presents a scalable field-reconfigurable learning network and machine intelligence system that is reconfigured to match the architecture or processing flow of a selected deep learning neural network and well suited for combining neural network learning and logic reasoning. It partitions the N layers, clusters or stages of the selected learning network into multiple parts with inter-parts connections to a plural of field-reconfigurable processing modules. The inter-parts connections are configured into a field-reconfigurable processing and interconnection module. Multiple field-reconfigurable learning networks can be interconnected to produce a larger scale field-reconfigurable learning network, and can be connected to the Internet to provide a field-reconfigurable learning network cloud service. | 2019-05-09 |
20190138891 | APPARATUS AND METHOD WITH NEURAL NETWORK - A neural network apparatus includes a plurality of node buffers connected to a node lane and configured to store input node data by a predetermined bit size; a plurality of weight buffers connected to a weight lane and configured to store weights; and one or more processors configured to: generate first and second split data by splitting the input node data by the predetermined bit size, store the first and second split data in the node buffers, output the first split data to an operation circuit for a neural network operation on an index-by-index basis, shift the second split data, and output the second split data to the operation circuit on the index-by-index basis. | 2019-05-09 |
20190138892 | NEURAL NETWORK DEVICE AND METHOD - A method of performing operations on a plurality of inputs and a same kernel using a delay time by using a same processor, and a neural network device thereof are provided, the neural network device includes input data including a first input and a second input, and a processor configured to obtain a first result by performing operations between the first input and a plurality of kernels, to obtain a second result by performing operations between the second input, which is received at a time delayed by a first interval from a time when the first input is received, and the plurality of kernels, and to obtain output data using the first result and the second result. The neural network device may include neuromorphic hardware and may perform convolutional neural network (CNN) mapping. | 2019-05-09 |
20190138893 | APPLICATIONS OF BACK-END-OF-LINE (BEOL) CAPACITORS IN COMPUTE-IN-MEMORY (CIM) CIRCUITS - An apparatus is described. The apparatus includes a compute-in-memory (CIM) circuit for implementing a neural network disposed on a semiconductor chip. The CIM circuit includes a mathematical computation circuit coupled to a memory array. The memory array includes an embedded dynamic random access memory (eDRAM) memory array. Another apparatus is described. The apparatus includes a compute-in-memory (CIM) circuit for implementing a neural network disposed on a semiconductor chip. The CIM circuit includes a mathematical computation circuit coupled to a memory array. The mathematical computation circuit includes a switched capacitor circuit. The switched capacitor circuit includes a back-end-of-line (BEOL) capacitor coupled to a thin film transistor within the metal/dielectric layers of the semiconductor chip. Another apparatus is described. The apparatus includes a compute-in-memory (CIM) circuit for implementing a neural network disposed on a semiconductor chip. The CIM circuit includes a mathematical computation circuit coupled to a memory array. The mathematical computation circuit includes an accumulation circuit. The accumulation circuit includes a ferroelectric BEOL capacitor to store a value to be accumulated with other values stored by other ferroelectric BEOL capacitors. | 2019-05-09 |
20190138894 | ANALOG NEUROMORPHIC CIRCUITS FOR DOT-PRODUCT OPERATION IMPLEMENTING RESISTIVE MEMORIES - An analog neuromorphic circuit is disclosed having resistive memories that provide a resistance to each corresponding input voltage signal. Input voltages are applied to the analog neuromorphic circuit. Each input voltage represents a vector value that is a non-binary value included in a vector that is incorporated into a dot-product operation with weighted matrix values included in a weighted matrix. A controller pairs each resistive memory with another resistive memory. The controller converts each pair of resistance values to a single non-binary value. Each single non-binary value is mapped to a weighted matrix value included in the weighted matrix that is incorporated into the dot-product operation with the vector values included in the vector. The controller generates dot-product operation values from the dot-product operation with the vector and the weighted matrix where each dot-product operation is a non-binary value. | 2019-05-09 |
20190138895 | MODEL MATCHING AND LEARNING RATE SELECTION FOR FINE TUNING - A method, computer system, and computer program product for model selection for training a new dataset is provided. The present invention may include choosing a model from a set of models to be evaluated for training the new dataset, selecting a sample input from a subset of the new dataset, calculating a model activation score for each of the sample inputs in the chosen model, calculating an accumulated model activation score for the chosen model, depending on the model activation score of each of the sample inputs in the chosen model, calculating an accumulated model activation score for each model from the set of models to be evaluated for training the new dataset, and selecting the model for training the new dataset with the highest accumulated model activation score. | 2019-05-09 |
20190138896 | Method for Optimizing Neural Networks - A method includes: providing a deep neural networks (DNN) model comprising a plurality of layers, each layer of the plurality of layers includes a plurality of nodes; sampling a change of a weight for each of a plurality of weights based on a distribution function, each weight of the plurality of weights corresponds to each node of the plurality of nodes; updating the weight with the change of the weight multiplied by a sign of the weight; and training the DNN model by iterating the steps of sampling the change and updating the weight. The plurality of weights has a high rate of sparsity after the training. | 2019-05-09 |
20190138897 | SYSTEM AND METHOD FOR CIRCUIT SIMULATION BASED ON RECURRENT NEURAL NETWORKS - According to one embodiment of the present invention a circuit simulator configured to simulate a degraded output of a circuit including a plurality of transistors includes: a behavioral recurrent neural network configured to receive an input waveform and to compute a circuit output waveform; a feature engine configured to model one or more degraded circuit elements in accordance with an aging time, to receive the circuit output waveform and to output a plurality of degraded features; and a physics recurrent neural network configured to receive the plurality of degraded features from the feature engine and to simulate the degraded output of the circuit. | 2019-05-09 |
20190138898 | METHOD AND APPARATUS WITH NEURAL NETWORK PERFORMING DECONVOLUTION - A neural network apparatus configured to perform a deconvolution operation includes a memory configured to store a first kernel; and a processor configured to: obtain, from the memory, the first kernel; calculate a second kernel by adjusting an arrangement of matrix elements comprised in the first kernel; generate sub-kernels by dividing the second kernel; perform a convolution operation between an input feature map and the sub-kernels using a convolution operator; and generate an output feature map, as a deconvolution of the input feature map, by merging results of the convolution operation. | 2019-05-09 |
20190138899 | PROCESSING APPARATUS, PROCESSING METHOD, AND NONVOLATILE RECORDING MEDIUM - A technique capable of providing a new function usable as an activation function is provided. An inference apparatus includes a receiving unit that receives input of target data; and an inference unit that executes a predetermined inference process with respect to the target data using a neural network model. The neural network model includes a plurality of processing layers, and, as the processing layers, one or more activation function layers that convert an input value by a predetermined activation function. The activation function of at least one of the activation function layers is configured as a function of a waveform the output value of which changes, in a first range, to approach a maximum value as an input value increases and, in a second range, away from a minimum value as the input value increases, such that the output values in the first and second ranges are not the same. | 2019-05-09 |
20190138900 | NEURON CIRCUIT, SYSTEM, AND METHOD WITH SYNAPSE WEIGHT LEARNING - A neuron circuit performing synapse learning on weight values includes a first sub-circuit, a second sub-circuit, and a third sub-circuit. The first sub-circuit is configured to receive an input signal from a pre-synaptic neuron circuit and determine whether the received input signal is an active signal having an active synapse value. The second sub-circuit is configured to compare a first cumulative reception counter of active input signals with a learning threshold value based on results of the determination. The third sub-circuit is configured to perform a potentiating learning process based on a first probability value to set a synaptic weight value of at least one previously received input signal to an active value, upon the first cumulative reception counter reaching the learning threshold value, and perform a depressing learning process based on a second probability value to set each of the synaptic weight values to an inactive value. | 2019-05-09 |
20190138901 | TECHNIQUES FOR DESIGNING ARTIFICIAL NEURAL NETWORKS - Systems and methods for identifying at least one neural network suitable for a given application are provided. A candidate set of neural network parameters associated with a candidate neural network is selected. At least one performance characteristic of the candidate neural network is predicted. The at least one performance characteristic of the candidate neural network is compared against a current performance baseline. When the at least one performance characteristic exceeds the current performance baseline, using a predetermined training dataset is used to train and test the candidate neural network for identifying the at least one suitable neural network. | 2019-05-09 |
20190138902 | METHODS AND SYSTEMS FOR IMPROVED TRANSFORMS IN CONVOLUTIONAL NEURAL NETWORKS - A system and method for an improved convolutional layer in convolutional neural networks is provided. The convolution is performed via a transformation that includes relocating input, relocating convolution filters and performing an aggregate matrix multiply. | 2019-05-09 |
20190138903 | REDUCING THE COST OF N MODULAR REDUNDANCY FOR NEURAL NETWORKS - An N modular redundancy method, system, and computer program product include a computer-implemented N modular redundancy method for neural networks, the method including selectively replicating the neural network by employing one of checker neural networks and selective N modular redundancy (N-MR) applied only to critical computations. | 2019-05-09 |
20190138904 | TRAINING AND/OR UTILIZING AN INTERACTION PREDICTION MODEL TO DETERMINE WHEN TO INTERACT, AND/OR PROMPT FOR INTERACTION, WITH AN APPLICATION ON THE BASIS OF AN ELECTRONIC COMMUNICATION - Training and/or utilizing an interaction prediction model to generate a predicted interaction value that indicates a likelihood of interaction with a corresponding application on the basis of an electronic communication. The application can be in addition to any electronic communication application that is utilized in formulating the electronic communication and/or that is utilized in rendering the electronic communication. The predicted interaction value can be generated based on processing, utilizing the interaction prediction model, of features of the electronic communication and/or of other features. The predicted interaction value can be utilized to determine whether to perform further action(s) that interact with, and/or enable efficient interaction with, the application on the basis of the electronic communication. | 2019-05-09 |
20190138905 | TRACEABILITY SYSTEMS AND METHODS - The systems and methods provide an action recognition and analytics tool for use in manufacturing, health care services, shipping, retailing, restaurants and other similar contexts. Machine learning action recognition can be utilized to determine cycles, processes, actions, sequences, objects and or the like in one or more sensor streams. The sensor streams can include, but are not limited to, one or more video sensor frames, thermal sensor frames, infrared sensor frames, and or three-dimensional depth frames. The analytics tool can provide for establishing traceability. | 2019-05-09 |
20190138906 | REDUCING PROBLEM COMPLEXITY WHEN ANALYZING 3-D IMAGES - A method for training a deep learning algorithm using N-dimensional data sets may be provided. Each data set comprises a plurality of N-1-dimensional data sets. The method comprises selecting a batch size and assembling an equally sized training batch. The samples are selected to be evenly distributed within said respective N-dimensional data sets. The method comprises also starting from a predetermined offset number, wherein the number of samples is equal to the selected batch size number, and feeding said training batches of N-1-dimensional samples into a deep learning algorithm for the training. Upon the training resulting in a learning rate that is below a predetermined level, selecting a different offset number for at least one of said N-dimensional data sets, and going back to the step of assembling. Upon the training resulting in a learning rate that is equal or higher than said predetermined level, the method stops. | 2019-05-09 |
20190138907 | Unsupervised Deep Learning Biological Neural Networks - An experience-based expert system includes an open-set neural net computing sub-system having massive parallel distributed hardware processing associated massive parallel distributed software configured as a natural intelligence biological neural network that maps an open set of inputs to an open set of outputs. The sub-system can be configured to process data according to the Boltzmann Wide-Sense Ergodicity Principle; to process data received at the inputs to determine an open set of possibility representations; to generate fuzzy membership functions based on the representations; and to generate data based on the functions and to provide the data at the outputs. An external intelligent system can be coupled for communication with the sub-system to receive the data and to make a decision based on the data. The external system can include an autonomous vehicle. The decision can determine a speed of the vehicle or whether to stop the vehicle. | 2019-05-09 |
20190138908 | ARTIFICIAL INTELLIGENCE INFERENCE ARCHITECTURE WITH HARDWARE ACCELERATION - Various systems and methods of artificial intelligence (AI) processing using hardware acceleration within edge computing settings are described herein. In an example, processing performed at an edge computing device includes: obtaining a request for an AI operation using an AI model; identifying, based on the request, an AI hardware platform for execution of an instance of the AI model; and causing execution of the AI model instance using the AI hardware platform. Further operations to analyze input data, perform an inference operation with the AI model, and coordinate selection and operation of the hardware platform for execution of the AI model, is also described. | 2019-05-09 |
20190138909 | METHOD FOR USING DNA TO STORE TEXT INFORMATION, DECODING METHOD THEREFOR AND APPLICATION THEREOF - A method for encoding and storing text information using DNA as a storage medium, a decoding method therefor and an application thereof. The method for using DNA to store text information comprises: encoding characters into computer binary digits by means of encoding, and converting the binary digits into DNA sequences by means of transcoding; and artificially synthesizing the DNA sequences encoded with character information, positioning the characters by means of a designed ligation adapter, and assembling the DNA sequences encoded with the character information according to a pre-set order. The method for using DNA to store text information has the advantages of a small storage volume, a large storage capacity, a strong stability and low maintenance costs. | 2019-05-09 |
20190138910 | SYSTEM AND METHOD FOR DETERMINING OPTIMAL SOLUTION IN A SWARM OF SOLUTIONS USING SWARM INTELLIGENCE - A system and method for determining an optimal solution to an optimization problem in a swarm of candidate solutions is provided. The invention comprises generating a population of random particles, where each particle is representative of a candidate solution. Further, a best particle is identified from the generated population of particles. The best particle is representative of an optimal solution. The population of particles is categorised into similar and non-similar particle groups by applying one or more multivariate measurement techniques, and similarity between the particles of the non-similar particle group with best particle is updated by applying an imitation technique. The generated population is updated with updated particles and a new best particle is evaluated from said population. Furthermore, final best particle is determined by further updating the population of particles until one or more target conditions are achieved. | 2019-05-09 |
20190138911 | Channel Based Corpus Management - An approach is provided in which a channel sensitive knowledge manager receives content segments over multiple different source channels, and annotates the content segments with channel type tags corresponding to their respective source channel. Then, the channel sensitive knowledge manager receives a request from a user over a user interface and matches the user interface to one of the source channels. The channel sensitive knowledge manager identifies a set of the content segments that are annotated with a channel type tag corresponding to the match source channel. In turn, the channel sensitive knowledge manager generates answers to the request using the identified set of content segments and sends the answers to the user over the user interface. | 2019-05-09 |
20190138912 | DETERMINING INSIGHTS FROM DIFFERENT DATA SETS - Systems, methods, and non-transitory computer-readable media (systems) are disclosed for generating an analytics insight from a data set based on learning from a different data set. In particular, in one or more embodiments, the disclosed systems analyze a first data set to determine significant features related to an analytics metric. The disclosed systems determine a correlation between features of a second data set and the significant features of the first data set. Furthermore, in one or more embodiments, the disclosed systems utilize the correlation to generate an analytics insight, such as insights on segment of users. In one or more embodiments, the first data set and the second data set contain different features and/or different users and the second data set lacks data regarding the analytics metric. | 2019-05-09 |
20190138913 | PREDICTION MODEL GENERATION DEVICE, PREDICTION MODEL GENERATION METHOD, AND RECORDING MEDIUM - A prediction model generation device has a first storage unit that stores a plurality of explanatory variables, a second storage unit that stores a plurality of objective variables, an input unit that inputs instruction information on classification, a class generation unit that generates a plurality of classes based on the instruction information, and a prediction model calculation unit that calculates a plurality of prediction models corresponding to the plurality of classes. The prediction model calculation unit has a learning data set extraction unit that extracts a learning data set corresponding to each of the plurality of classes from among the plurality of explanatory variables and the plurality of objective variables. | 2019-05-09 |
20190138914 | AUTONOMOUS BOT PERSONALITY GENERATION AND RELATIONSHIP MANAGEMENT - Certain aspects of the technology disclosed involve systems and methods for a bot ecosystem having a social network layer and a knowledgebase layer. Bots can be generated having attribute data that define a personality of the bot. Tokens can be mined by bots via contribution to the knowledge base and interacting with other bots. Relationships among bots are managed according to preconfigured settings. Bots can be influenced and trained by updating attribute data based on interaction information. | 2019-05-09 |
20190138915 | COMMUNICATION GENERATION IN COMPLEX COMPUTING NETWORKS - This disclosure is directed to communication generation by traversing routes of a graph in a complex computing network. The communication generation is used for determining whether an input signal has certain desired signal attributes. | 2019-05-09 |
20190138916 | COGNITIVE SYSTEM TO ITERATIVELY EXPAND A KNOWLEDGE BASE - Aspects include creating a knowledge base that identifies experts in a set of domains. Front-end processing is provided to an issue tracking system. The front-end processing includes receiving a report of an issue related to one of the domains, and accessing the knowledge base to locate an expert in the domain. The front-end processing also includes instructing the issue tracking system to route the received report of the issue to the located expert in the domain. The issue tracking system executes on a different processor than the front-end processing. Data collected from operation of the issue tracking system is monitored, and the knowledge base is updated based at least in part on the data collected from the operation of the issue tracking system. | 2019-05-09 |
20190138917 | Behavioral Prediction for Targeted End Users - Behavioral prediction for targeted end users is described. In one or more example embodiments, a computer-readable storage medium has multiple instructions that cause one or more processors to perform multiple operations. Targeted selectstream data is obtained from one or more indications of data object requests corresponding to a targeted end user. A targeted directed graph is constructed based on the targeted selectstream data. A targeted graph feature vector is computed based on one or more invariant features associated with the targeted directed graph. A behavioral prediction is produced for the targeted end user by applying a prediction model to the targeted graph feature vector. In one or more example embodiments, the prediction model is generated based on multiple graph feature vectors respectively corresponding to multiple end users. In one or more example embodiments, a tailored opportunity is determined responsive to the behavioral prediction and issued to the targeted end user. | 2019-05-09 |
20190138918 | SYSTEM AND METHOD FOR PROVIDING DISTRIBUTED INTELLIGENT ASSISTANCE - A system and a method for a service engine providing distributed intelligent assistance to a user are described herein. The method comprising steps of receiving and displaying a user inquiry from the user, the user inquiry having a linguistic pattern including a verb; generating and displaying a follow up question based on the user inquiry; receiving and displaying a follow up answer from the user; and generating and displaying a response based on the user inquiry and the follow up answer. | 2019-05-09 |
20190138919 | METHODS AND SYSTEMS FOR PRELOADING APPLICATIONS AND GENERATING PREDICTION MODELS - An application preloading method and apparatus, and a prediction model generation method and apparatus are described. Application preloading may include obtaining application usage state information of a terminal and contextual information of the terminal; inputting the obtained application usage state information and contextual information into a pre-generated prediction model that is configured for predicting application startup and for calculating at least one prediction value for the application startup; determining an application to be started according to the at least one prediction value, and preloading the application to be started. The prediction model may be pre-generated according to usage association information of applications within a predetermined time period and contextual information of the terminal corresponding to the usage association information. | 2019-05-09 |
20190138920 | SELF-ADAPTIVE SYSTEM AND METHOD FOR LARGE SCALE ONLINE MACHINE LEARNING COMPUTATIONS - Aspects of the present disclosure involve systems, methods, devices, and the like for generating a self-adaptive system for large scale online machine learning computations. In one embodiment, a system is introduced that can generate and execute an optimization plan for combining nodes based on relationship information. The execution of the optimization plan can occur at both a static and dynamic state to determine how to best execute node combining. In another embodiment, pool isolation is executed base on the processing information associated with each node. | 2019-05-09 |
20190138921 | INTERACTIVE GUIDANCE SYSTEM FOR SELECTING THERMODYNAMICS METHODS IN PROCESS SIMULATIONS - A simulation tool executing a simulation model and a generating an automated dialog associated therewith. The automated dialog comprises a bot configured for interacting with a user, wherein the dialog is displayed to the user. The bot is integrated with a set of rules that are referenced as a function of input received from the user for furthering the dialog and making a recommendation about the process simulation. In certain embodiments, the simulation tool is configured to select a thermodynamic method for use in a process simulation as a function of the set of rules and the user input. | 2019-05-09 |
20190138922 | Apparatus and methods for forward propagation in neural networks supporting discrete data - Aspects for forward propagation of a multilayer neural network (MNN) in a neural network processor are described herein. As an example, the aspects may include a computation module that includes a master computation module and one or more slave computation modules. The master computation module may be configured to receive one or more groups of MNN data. The one or more groups of MNN data may include input data and one or more weight values and wherein at least a portion of the input data and the weight values are stored as discrete values. The one or more slave computation modules may be configured to calculate one or more groups of slave output values based on a data type of each of the one or more groups of MNN data. | 2019-05-09 |
20190138923 | SYSTEM AND METHOD FOR OBTAINING AND TRANSFORMING INTERACTIVE NARRATIVE INFORMATION - A system and method for obtaining and transforming interactive narrative data comprise a creation space configured to present a predetermined narrative structure and configured to obtain narrative responses from at least one individual, with the narrative responses are discretized according to story acts. A custom ontology is developed for applying sentiment analysis to each of the discretized story acts with a qualitative and quantitative emotional value applied to each, and a processor determines a story arc corresponding to the emotional values, with an emotional profile developed for the individual based on the story arc. | 2019-05-09 |
20190138924 | QUANTUM MECHANICAL PROPABILISTIC APPARATUS TO MEASURE, FORECAST, VISUALIZE HUMANOID MENTAL STATUSES - This invention is a quantum mechanical probabilistic apparatus measuring, forecasting and visualising human mental statuses. The quantum mechanical probabilistic apparatus encodes observables into quantum information and decodes quantum information into observables on conventional computer hardware and quantum computer hardware. The quantum mechanical probabilistic apparatus detects measuring apparatus biasing interferences with the observed and avoids contamination with the measured environment. The quantum mechanical probabilistic apparatus learns emotional and mental states of humans and predicts the future path of emotional, mental states of once catalogued humans. The quantum mechanical probabilistic apparatus simulates emotional, mental states of humans and communicates with humans as autonomous identity. The quantum mechanical probabilistic apparatus utilises the apparatus measured, forecasted and algorithmic calculated emotional, mental states of observed humans as password and passcode to uniquely identify the humans under observation. Every new observation results in quantum mechanical probabilistic unique measure and forecast and new and unique passwords and/or passcodes. | 2019-05-09 |
20190138925 | TERMINAL DEVICE FOR GENERATING USER BEHAVIOR DATA, METHOD FOR GENERATING USER BEHAVIOR DATA AND RECORDING MEDIUM - A terminal device for generating user behavior data, a method for generating user behavior data, and a recording medium are provided. The disclosed terminal device may include a memory unit storing instructions readable by a computer; and a processor unit implemented to execute the instructions, where the processor unit may compute a probability distribution model for achieving the intentions of a user by using raw data related to time-dependent actions of the user and may generate user behavior data by using the probability distribution model, with the user behavior data comprising time series data in which multiple actions composing the intentions of the user are aligned in order. | 2019-05-09 |
20190138926 | Degradation modeling and lifetime prediction method considering effective shocks - A degradation modeling and lifetime prediction method considering effective shocks includes steps of: first collecting degradation test data, then establishing a performance degradation model, and determining an environment or load changing rate threshold of a product subjected to effective shock based on the test data; estimating parameters in the model, and determining effective shock occurrence times based on the future environmental or load profile, and finally preforming lifetime and reliability prediction. Specific steps are as follows: step 1: collecting degradation test data; step 2: establishing a degradation model; step 3: determining an environment or load changing rate threshold; step 4: estimating the parameters; step 5: predicting the times that effective shocks occur; and step 6: performing reliability prediction. The present invention considers effects of effective shocks caused by sharp environment or load changes on product performance degradation, which makes the prediction method more realistic and improves the prediction accuracy. | 2019-05-09 |
20190138927 | DATABASE UTILIZING SPATIAL PROBABILITY MODELS FOR DATA COMPRESSION - A method, article comprising machine-readable instructions and apparatus that processes data systems for encoding, decoding, pattern recognition/matching and data generation is disclosed. State subsets of a data system are identified for the efficient processing of data based, at least in part, on the data system's systemic characteristics. | 2019-05-09 |
20190138928 | QUANTUM NETWORK NODE AND PROTOCOLS WITH MULTIPLE QUBIT SPECIES - The disclosure describes aspects of using multiple species in trapped-ion nodes for quantum networking. In an aspect, a quantum networking node is described that includes multiple memory qubits, each memory qubit being based on a | 2019-05-09 |
20190138929 | SYSTEM AND METHOD FOR AUTOMATIC BUILDING OF LEARNING MACHINES USING LEARNING MACHINES - Systems, devices and methods are provided for building learning machines using learning machines. The system generally includes a reference learning machine, a target learning machine being built, a component analyzer module configured to analyze inputs from the reference learning machine, the target learning machine, a set of test signals, and a list of components in the reference learning machine and the target learning machine, and return a set of output values for each component on the list of components. The system further includes a component tuner module configured to modify different components in the target learning machine based on the set of output values and a component mapping, thereby resulting in a tuned learning machine. | 2019-05-09 |
20190138930 | SYSTEMS AND METHODS FOR REAL-TIME DATA PROCESSING ANALYTICS ENGINE WITH ARTIFICIAL INTELLIGENCE FOR TARGET INFORMATION PROTECTION - Example implementations are directed to systems and methods to process content employing a model for characterizing targeted content where the model is trained to flag indefinable user information; analyze the content to develop a sensitive data index based on content that is flagged by the model; and apply machine learning to generate characterization data and contextual data for the information associated with one or more users based on the sensitive data index, where the machine learning utilizes content adjacent to the information associated with one or more users and the sensitive data index in a neural network to output substitute terms. | 2019-05-09 |
20190138931 | APPARATUS AND METHOD OF INTRODUCING PROBABILITY AND UNCERTAINTY VIA ORDER STATISTICS TO UNSUPERVISED DATA CLASSIFICATION VIA CLUSTERING - In a host device, a method for stabilizing a data training set comprises generating, by the host device, a data training set based upon a set of data elements received from a computer infrastructure; applying, by the host device, multiple iterations of a classification function to the data training set to generate a set of data element groups; dividing, by the host device, the set of data element groups resulting from the multiple iterations of the clustering function into multiple time intervals; for each time interval of the multiple time intervals, deriving, by the host device, a maximum threshold and a minimum threshold for each data element groups of the set of data element groups included in the time interval; applying an order statistic function to the maximum thresholds and the minimum thresholds for each time interval; and identifying a relative variability among the ordered maximum thresholds. | 2019-05-09 |
20190138932 | REAL TIME ANOMALY DETECTION SYSTEMS AND METHODS - The systems and methods provide an action recognition and analytics tool for use in manufacturing, health care services, shipping, retailing and other similar contexts. Machine learning action recognition can be utilized to determine cycles, processes, actions, sequences, objects and or the like in one or more sensor streams. The sensor streams can include, but are not limited to, one or more video sensor frames, thermal sensor frames, infrared sensor frames, and or three-dimensional depth frames. The analytics tool can provide for process validation, anomaly detection and in-process quality assurance. | 2019-05-09 |
20190138933 | DATA AMOUNT COMPRESSING METHOD, APPARATUS, PROGRAM, AND IC CHIP - A data amount compressing method for compressing a data amount corresponding to a learned model obtained by letting the learning model learn a predetermined data group, the learning model having a tree structure in which multiple nodes associated with respective hierarchically divided state spaces are hierarchically arranged, wherein each node in the learned model is associated with an error amount that is generated in the process of the learning and corresponds to prediction accuracy, and the data amount compressing method includes: a reading step of reading the error amount associated with each node; and a node deleting step of deleting a part of the nodes of the learned model according to the error amount read in the reading step, thereby compressing the data amount corresponding to the learned model. | 2019-05-09 |
20190138934 | TECHNOLOGIES FOR DISTRIBUTING GRADIENT DESCENT COMPUTATION IN A HETEROGENEOUS MULTI-ACCESS EDGE COMPUTING (MEC) NETWORKS - Systems, apparatuses, methods, and computer-readable media, are provided for distributed machine learning (ML) training using heterogeneous compute nodes in a heterogeneous computing environment, where the heterogeneous compute nodes are connected to a master node via respective wireless links. ML computations are performed by individual heterogeneous compute nodes on respective training datasets, and a master combines the outputs of the ML computations obtained from individual heterogeneous compute nodes. The ML computations are balanced across the heterogeneous compute nodes based on knowledge of network conditions and operational constraints experienced by the heterogeneous compute nodes. Other embodiments may be described and/or claimed. | 2019-05-09 |
20190138935 | CLASSIFICATION OF MEMBERS IN A SOCIAL NETWORKING SERVICE - A method and apparatus for scoring member data in a social networking service is provided. A method comprises receiving input that indicates a particular feature that is not in a set of features upon which a first model is based. In response to receiving the input, training a plurality of models based on training data and a plurality of features that includes the set of features and the particular feature, and selecting, based on one or more criteria, a particular model from among the plurality of models that includes a second model that is of the same type as the first model. Using the particular model to score a particular data set based on the plurality of features indicated in the particular data set. | 2019-05-09 |
20190138936 | LEARNED MODEL INTEGRATION METHOD, APPARATUS, PROGRAM, IC CHIP, AND SYSTEM - A learned model integration method for integrating multiple different learned models obtained by letting a learning model learn a predetermined data group, the learning model having a tree structure in which multiple nodes associated with respective hierarchically divided state spaces are hierarchically arranged, the method includes: a data reading step of reading data related to the multiple different learned models from a predetermined memory unit; and an integrating step in which, for each node constituting a tree structure related to the multiple different learned models, when a node exists in only one learned model, the node is duplicated, and when nodes exist in corresponding positions in the multiple learned models, the corresponding nodes are integrated, thereby integrating the multiple different learned models into a single learned model. | 2019-05-09 |
20190138937 | SELF-LEARNING CONTEXTUAL MODALITY SELECTION FOR COGNITIVE SOLUTION DELIVERY - A problem context is computed from an input at an application. The problem context includes a set of problem factors, the input including a problem to be solved using a cognitive system. A user context is computed from the input at the application, the user context including a set of user factors. A type of media is determined corresponding to a complexity of a cognitive solution received from the cognitive system, where the cognitive solution is in response to the problem. Using a problem factor from the set of problem factors, using a user factor in the set of user factors, and the complexity, a mode of communication is determined. A communication apparatus is adjusted to cause a data communication to occur and deliver the cognitive solution in the type of media using the mode of communication. | 2019-05-09 |