25th week of 2022 patent applcation highlights part 62 |
Patent application number | Title | Published |
20220198182 | METHODS AND SYSTEMS OF FIELD DETECTION IN A DOCUMENT - Systems and methods are disclosed to receive a training data set comprising a plurality of document images, wherein each document image of the plurality of document images is associated with respective metadata identifying a document field containing a variable text; generate, by processing the plurality of document images, a first heat map represented by a data structure comprising a plurality of heat map elements corresponding to a plurality of document image pixels, wherein each heat map element stores a counter of a number of document images in which the document field contains a document image pixel associated with the heat map element; receive an input document image; and identify, within the input document image, a candidate region comprising the document field, wherein the candidate region comprises a plurality of input document image pixels corresponding to heat map elements satisfying a threshold condition. | 2022-06-23 |
20220198183 | INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM - An information processing apparatus includes a processor configured to: receive an image on a paper sheet having an entry field ready to be filled with information; and present in a user selectable manner three production methods to produce definition information indicating an attribute of information to fill in the entry field, the three production methods including a method in which a user newly produces definition information, a method of reusing definition information that has been produced for another paper sheet and is prepared beforehand, and a method of producing definition information by using results provided by an artificial intelligence having sorted the received paper sheet. | 2022-06-23 |
20220198184 | INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM - An information processing apparatus includes a processor configured to receive, if an error is found in sorting of a form image after an operator checks and corrects a result of character recognition performed on the sorted form image, an instruction to cause a process to revert to the sorting for the form image. | 2022-06-23 |
20220198185 | FINDING NATURAL IMAGES IN DOCUMENT PAGES - An image processing method includes: generating, from combined connected components (CCs) of a document image, candidate text CCs, candidate background CCs, and candidate natural image CCs where the candidate background CCs are excluded from the combined CCs to generate the candidate natural image CCs with a predetermined criterion dependent on the candidate text CCs; generating a final natural image bounding box by expanding a candidate natural image bounding box of the candidate natural image CCs and including in the expanded candidate natural image bounding box at least one combined CC that intersects the expanded candidate natural image bounding box; and modifying, based on the final natural image bounding box, the document image and displaying the modified document image to a user. | 2022-06-23 |
20220198186 | SYNTHESIZING HARD-NEGATIVE TEXT TRAINING DATA - A method for synthesizing negative training data associated with training models to detect text within documents and images. The method includes one or more computer processors receiving a set of dictates associated with generating one or more negative training datasets for training a set of models to classify a plurality of features found within a data source. The method further includes identifying a set of rules related to generating negative training data to detect text based on the received set of dictates. The method further includes compiling one or more arrays of elements of hard-negative training data into a negative training data dataset based on the identified set of rules and one or more dictates. The method further includes determining metadata corresponding an array of elements of hard-negative training data. | 2022-06-23 |
20220198187 | EXTRACTING MULTIPLE DOCUMENTS FROM SINGLE IMAGE - System and method for document image detection, comprising: producing, using a neural network, a superpixel segmentation map of an input image; generating a superpixel binary mask by associating each superpixel of the superpixel segmentation map with a class of a predetermined set of classes; identifying one or more connected components in the superpixel binary mask; for each connected component of the superpixel binary mask, identifying a corresponding minimum bounding polygon; creating one or more image dividing lines based on the minimum bounding polygons; and defining boundaries of one or more objects of interest based on at least a subset of the image dividing lines. | 2022-06-23 |
20220198188 | ZERO-FOOTPRINT IMAGE CAPTURE BY MOBILE DEVICE - A computer-implemented method for image capture by a mobile device, comprising: receiving, by a video capturing application running on a mobile device, a video stream from a camera of the mobile device; identifying a specific frame of the video stream; generating a plurality of hypotheses defining image borders within the specific frame; selecting, by a neural network, a particular hypothesis among the plurality of hypotheses; producing a candidate image by applying the particular hypothesis to the specific frame; determining a value of a quality metric of the candidate image; determining that the value of the quality metric of the candidate image exceeds one or more values of the quality metric of one or more previously processed images extracted from the video stream; wherein the image capture application is a zero-footprint application | 2022-06-23 |
20220198189 | Statistical Data Fingerprinting and Tracing Data Similarity of Documents - A method and computing device for statistical data fingerprinting and tracing data similarity of documents. The method comprises applying a statistical function to a subset of text in a first document thereby generating a first fingerprint; applying the statistical function to a subset of text in a second document thereby generating a second fingerprint; comparing the first fingerprint to the second fingerprint; and determining that the subset of text in the first document matches the subset of text in the second document based on the first fingerprint threshold matching the second fingerprint, wherein the statistical function is a measure of randomness of a count of each character in a subset of text against an expected distribution of said characters. | 2022-06-23 |
20220198190 | INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM - An information processing apparatus includes a processor configured to control a display such that a result of recognition, which is obtained by recognizing an image on which a character string is written, and a result of comparison, which is obtained by comparing the result of recognition with a database registered in advance, are displayed next to each other. | 2022-06-23 |
20220198191 | REMOTE INSPECTION AND APPRAISAL OF BUILDINGS - A building appraisal system conducted by a remote inspector located away from a building. A processor coupled to an image sensor is configured to receive a gross floor area of the building. Images of an interior room of the building are stored in memory. The processor determines a planar surface in the images corresponding to a floor surface of the interior room and a plurality of corners in the images forming vertices of a bounded floor area on the floor surface. The processor computes an adjusted floor area of the building that includes the bounded floor area subtracted from the gross floor area. | 2022-06-23 |
20220198192 | CONTEXTUAL INFORMATION DISPLAYABLE ON WEARABLE DEVICES BASED ON IMAGES CAPTURED DURING WELLSITE OPERATIONS - A method includes receiving an image that includes a wellbore component used during a wellbore operation of a borehole at a wellsite captured by a camera at the wellsite and inputting the image into an image recognition model. The method includes outputting, from the image recognition model, a class representing the wellbore component and inputting the class into a context model. The method includes outputting, from the context model, contextual data related to the wellbore component based on, the class representing the wellbore component, contextual data relating to the wellbore operation, and a type of the wellbore operation. The method includes transmitting the contextual data to a wearable device worn by a user at the wellsite. | 2022-06-23 |
20220198193 | INFORMATION DISPLAY DEVICE, INFORMATION DISPLAY METHOD AND PROGRAM - An information display device includes: an acquisition unit that acquires a plurality of sensing data acquired by a sensor provided on a flight device by sensing a sensed object to be sensed at a plurality of flying positions of the flight device when the flight device flies, a plurality of sensing positions at which the plurality of the sensing data are acquired, respectively, and a plurality of directional information each indicating a direction of the sensed object when each of the plurality of sensing data is acquired; and a display control unit that causes a display unit to display the sensing data acquired by sensing the sensed object at each of the acquisition positions, and the directional information for indicating the direction of the sensed object when the sensing data is acquired at the acquisition position at each of the sensing positions, in association with each of the sensing positions, wherein the display control unit causes the display unit to display the sensing data acquired by sensing the sensed object at each of the sensing positions so as to be superimposed on a terrain image corresponding to each of the sensing positions. | 2022-06-23 |
20220198194 | METHOD OF EVALUATING EMPATHY OF ADVERTISING VIDEO BY USING COLOR ATTRIBUTES AND APPARATUS ADOPTING THE METHOD - Provided is an empathy evaluation method and apparatus using video characteristics information. The empathy evaluation method includes establishing a video database by collecting a plurality of video clips, classifying and labeling each of the video clips by empathy, preparing training data by extracting a region of interest (ROI) video from each of the video clips and extracting physical characteristics from the ROI video, generating a video characteristics model file obtained through learning using the training data include 2 labels(empathy/non-empathy) vector that is calculated by the difference between the metric measurement size trained with respect to the video characteristics. Test video into the system can automatically judge the empathy evaluation of video. | 2022-06-23 |
20220198195 | SYSTEM AND METHOD FOR VIDEO ANALYTICS FOR THERMOGRAPHY PROCEDURE COMPLIANCE - Disclosed is a process for implementing an automated analytics for insuring compliance for a thermographic protocol for subjects seeking a temperature check, perhaps for entrance or access to a controlled space or facility. The automated video analytics utilize one or more cameras to detect thermography compliance violations based on whether the subject is perspiring, dehydrated, recently consumed a beverage, has exposed skin, excessive clothing, the amount and type of activity before getting screened, and/or the external and internal temperatures at the controlled facility associated with the subject. Furthermore, the automated video analytics may create a non-compliance score and/or control a timer for a non-compliance detection. Also, short and long term collected data may be analyzed for compliance to guidelines. | 2022-06-23 |
20220198196 | PROVIDING ACCESS TO AN AUTONOMOUS VEHICLE BASED ON USER'S DETECTED INTEREST - System and methods are provided that allow users of shared vehicles to benefit from an enhanced user experience that seamlessly unlocks and/or provides access to features for autonomous vehicles by proactively computing an interest index based on detected contextual behavioral patterns of the pedestrians such as the trajectory a candidate passenger is walking given a locational context. | 2022-06-23 |
20220198197 | LANE CURVATURE DETERMINATION - A computer includes a processor and a memory storing instructions executable by the processor to receive a series of sample coordinate points of a projected path of travel of a vehicle, generate interpolated coordinate points along the projected path between the sample coordinate points, fit a curve to the sample coordinate points and interpolated coordinate points, and output a curvature of a lane at a reported coordinate point along the projected path based on the curve. | 2022-06-23 |
20220198198 | SYSTEM AND METHOD FOR DETERMINING IMPLICIT LANE BOUNDARIES - A system and related method determines implicit lane boundaries by generating a bird's eye view of a portion of a road having a first lane and a second lane from environment data having information related to the road, overlaying a grid having cells onto the bird's eye view of the portion of the road, determining cells of the grid that form at least portions of the first lane of the road, determining cells of the grid that form at least portions of the second lane of the road, and determining a probability for one or more cells of the grid indicating a likelihood that a vehicle will travel upon portions of the road represented by the cells of the grid when traveling from the first lane to the second lane. The probability for one or more cells of the grid may be generated by a neural network trained with training data. | 2022-06-23 |
20220198199 | Stop Location Change Detection - The technology relates to approaches for determining appropriate stopping locations at intersections for vehicles operating in a self-driving mode. While many intersections have stop lines painted on the roadway, many others have no such lines. Even if a stop line is present, the physical location may not match what is in store map data, which may be out of date due to construction or line repainting. Aspects of the technology employ a neural network that utilizes input training data and detected sensor data to perform classification, localization and uncertain estimation processes. Based on these processes, the system is able to evaluate distribution information for possible stop locations. The vehicle uses such information to determine an optimal stop point, which may or may not correspond to a stop line in the map data. This information is also used to update the existing map data, which can be shared with other vehicles. | 2022-06-23 |
20220198200 | ROAD LANE CONDITION DETECTION WITH LANE ASSIST FOR A VEHICLE USING INFRARED DETECTING DEVICE - A system is provided for a vehicle having a front, a rear, a right side and a left side. The system includes an infrared detecting device mounted on the front of the vehicle. The infrared detecting device is constructed and arranged to 1) detect variations in road temperature and 2) detect heat tracks left on a road lane by preceding vehicles. A control unit is mounted in the vehicle and is connected to the infrared detecting device so as to process signals received from the infrared detecting device, the control unit being constructed and arranged 1) to predict road conditions based on the variations in road temperature detected by the infrared detecting device or 2) to predict road lane location, based on a path defined by the heat tracks detected by the infrared detecting device. | 2022-06-23 |
20220198201 | VEHICLE PARKING NAVIGATION - A sub-area in an area is identified as an authorized sub-area for a vehicle to access based on detecting a first object in the sub-area from first sensor data. Then a parameter of the first object is determined from the first sensor data. Upon detecting a second object in the sub-area from second sensor data, a parameter of the second object is determined based on the second sensor data. The sub-area is determined valid based on determining the parameter of the second object is different than the parameter of the first object. | 2022-06-23 |
20220198202 | CAMERA FOR VEHICLE AND PARKING ASSISTANCE APPARATUS HAVING THE SAME - According to at least one aspect, the present disclosure provides a vehicle camera comprising: a lens module; a circuit board including an image sensor configured to convert light incident through the lens module into an electrical signal; a front housing having the lens module coupled to a front side thereof and the circuit board coupled to a rear side thereof; a rear housing coupled to the rear side of the front housing and provided to surround the circuit board; an outer cover configured to surround at least a portion of the lens module, the outer cover including one or more infrared passing portions; and a depth camera module included inside the outer cover and coupled to the front side of the front housing, the depth camera module being configured to capture an image for detecting an obstacle around the vehicle using the infrared passing portion. | 2022-06-23 |
20220198203 | THREE DIMENSIONAL TRAFFIC SIGN DETECTION - Vehicles and methods for detecting a three-dimensional (3D) position of a traffic sign and controlling a feature of the vehicle based on the 3D position of the traffic sign. An image is received from a camera. The image is processed using a neural network. The neural network includes a traffic sign class block regressing a traffic sign class for a traffic sign included in the image and a rotation block regressing an orientation for the traffic sign. Dimensions for the traffic sign are retrieved from an information database based on the traffic sign class. A 3D position of the traffic sign is determined based on the dimensions of the traffic sign and the orientation of the traffic sign. A feature of the vehicle is controlled based on the 3D position of the traffic sign. | 2022-06-23 |
20220198204 | SYSTEMS AND METHODS FOR TRAFFIC LIGHT DETECTION AND CLASSIFICATION - In one embodiment, a traffic light classification system for a vehicle, includes an image capture device to capture an image of a scene that includes a traffic light with multiple light signals, a processor, and a memory communicably coupled to the processor and storing a first neural network module including instructions that when executed by the processor cause the processor to determine, based on inputting the image into a neural network, a semantic keypoint for each light signal in the traffic light, and determine, based on each semantic keypoint, a classification state of each light signal. | 2022-06-23 |
20220198205 | SYSTEM AND METHOD FOR CLASSIFICATION OF OBJECTS IN VEHICLE USING FEATURE VECTORS - The present disclosure relates to a system for differentiating objects present in a vehicle, the system includes one or more sensors placed within a vehicle to generate a set of signals in response to an object being present within the vehicle. An ADC converts the received set of signals to a digital form. A processor receives the digital set of signals, and process the received digital set of signals, to generate point cloud dataset. The processor extracts, from the point cloud dataset, a first set of features pertaining to a single frame and a second set of features pertaining to a multi-frame. The extracted set of features are provided as input to a classifier to differentiate the object present in one or more zones within the vehicle. | 2022-06-23 |
20220198206 | Biometrics Robustness Systems and Methods for Detecting Biometric Signals of a User and Adaptively Adjusting Signal Output to Control One or More Biometric Devices - Biometric robustness systems and methods are described for detecting biometric signals of a user and adaptively adjusting signal output to control biometric devices(s). In various aspects, the biometrics robustness systems and methods comprise determining a biometric signal pattern of the user based on analysis of biometric signals of the user. The biometric signals of the user are detected by one or more biometric sensors. The biometrics robustness systems and methods may comprise generating, by a processor communicatively coupled to the one or more biometric sensors, an adjusted control output based on an anomaly as detected within the biometric signal pattern. The biometrics robustness systems and methods may comprise providing, by the processor, an adjusted control output to a biometric device to control operation of the biometric device. | 2022-06-23 |
20220198207 | UPDATING METHOD FOR CONFIGURATION PARAMETERS OF ELECTRONIC DEVICE, DEVICE AND COMPUTER-READABLE MEDIUM - The present disclosure relates to an updating method for configuration parameters of an electronic device, a device and a computer-readable medium, wherein the updating method includes: acquiring fingerprint information collected by a fingerprint sensor at the electronic device; determining whether the fingerprint information is collected in a trusted mode; acquiring, in response to determining that the fingerprint information is collected in the trusted mode, a target configuration parameter of the electronic device for anti-spoofing detection according to the fingerprint information; and updating, in response to that the target configuration parameter of the electronic device and/or a current configuration parameter of the electronic device satisfies a preset condition, the current configuration parameter of the electronic device based on the target configuration parameter of the electronic device, wherein the current configuration parameter is used by the electronic device for anti-spoofing detection of a fingerprint in fingerprint information to be recognized. The solution of the present disclosure can update configuration parameters of the electronic device under certain conditions, thereby realizing high precision of anti-spoofing detection. | 2022-06-23 |
20220198208 | SYSTEMS AND METHODS FOR MASKING BIOMETRIC INFORMATION IN IMAGES - A method of securing biometric information may involve obtaining a digital image that contains biometric information. The method may involve identifying at least one region of the digital image that contains the biometric information and masking the biometric information. The biometric information may be a user's fingerprint and the user's fingerprint may be sufficiently masked that the masked fingerprint would not be accepted as authentic by most or all biometric authentication systems as matching the original fingerprint. | 2022-06-23 |
20220198209 | SYSTEM AND METHOD OF GENERATING BOUNDING POLYGONS - An example system includes a first and second digital device. The first digital device may be configured to provide an interface displaying an image including a depiction of an object, place a bounding shape around the object, and crop contents of the bounding shape to create a portion. The second digital device may be configured to receive the portion, retrieve high-level features and low-level features, apply first Atrous Spatial Pyramid Pooling (ASPP) to the high-level features to aggregate the high-level features as aggregate features, concatenate results to create the aggregate features, up-sample, apply a convolution to the low-level features, concatenate the aggregate features with the low-level features after convolution to form combined features, segment the combined features to generate a polygonal shape outline along outer boundaries of the first object, and provide the first polygonal shape outline to the first digital device for display. | 2022-06-23 |
20220198210 | INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM - An information processing apparatus includes a processor configured to: read character string information written on a paper document; obtain, from an external system that performs processing using the read character string information, external system information indicating a use condition relating to use of character string information in the external system; and determine whether the read character string information matches the external system information obtained from the external system. | 2022-06-23 |
20220198211 | AUTOMATIC STRUCTURING AND RETRIEVAL OF SPATIOTEMPORAL SEQUENCES OF CONTENT - One or more processor can automatically identify, structure and retrieve spatial and/or temporal sequences of digital media content according to semantic specification. Digital media content can be received and information from digital media content can be extracted. Based on the information, a knowledge graph can be constructed or structured to include at least one of spatial and temporal representation of the digital media content. A search query can be received associated with the digital media content. Based on traversing the knowledge graph structure according to at least one of spatial and temporal criterion mapped from the search query, new digital media content can be composed which meets the search query. | 2022-06-23 |
20220198212 | IMAGE CLASSIFICATION SYSTEM - An image classification system is provided for determining a likely classification of an image using multiple machine learning models that share a base machine learning model. The image classification system may be a browser-based system on a user computing device that obtains multiple machine learning models over a network from a remote system once, stores the models locally in the image classification system, and uses the models multiple times without needing to subsequently request the machine learning models again from the remote system. The image classification system may therefore determine likely a classification associated with an image by running the machine learning models on a user computing device. | 2022-06-23 |
20220198213 | METHOD FOR DETERMINING OPTIMAL ANOMALY DETECTION MODEL FOR PROCESSING INPUT DATA - Disclosed is a computer program stored in a computer readable storage medium according to an exemplary embodiment of the present disclosure. When the computer program is executed by one or more processors of a computing device, the computer program may perform operations for managing a model, and the operations may include: generating an anomaly detection model including a plurality of anomaly detection sub models having a pre-learned network function through using a plurality of training data subsets included in a training data set; determining one or more anomaly detection sub models for calculating an input data among the generated anomaly detection sub models; and judging whether or not the anomaly is existed in the input data through using the one or more determined anomaly detection sub models. | 2022-06-23 |
20220198214 | IMAGE RECOGNITION METHOD AND DEVICE BASED ON DEEP CONVOLUTIONAL NEURAL NETWORK - The present invention relates to the technical field of medical treatment, in particular to an image recognition method and device based on a deep convolutional neural network. The method comprises the following steps: pre-processing chest X-ray films to obtain initial X-ray film images that meets format requirements; screening the initial X-ray film images to detect whether they are posteroanterior chest images; inputting the posteroanterior chest images into a binary classification model of the deep convolutional neural network for negative and positive classification; inputting the images presenting positive results into a detection model of the deep convolutional neural network to detect a disease type and label an outline of a lesion area in each image; and displaying the disease type and lesion area corresponding to the image. According to the image recognition method based on the deep convolutional neural network provided by this embodiment of the present invention, whether the chest X-ray films are negative or positive can be screened, the lesion areas can also be positioned, and meanwhile, the types or signs of the diseases in the lesion areas can be labeled to provide doctors with more interpretable reference opinions. | 2022-06-23 |
20220198215 | METHOD, APPARATUS, AND COMPUTER PROGRAM PRODUCT FOR CHANGE DETECTION BASED ON DIGITAL SIGNATURES - A method, apparatus and computer program utilize digital signatures to accurately and efficiently identify changes to objects of interest within captured images. In the context of a method, a digital signature is obtained for an object of interest at a particular location. The method also determines whether a difference between the digital signature and a previously determined digital signature associated with the location satisfies a predefined criterion. In accordance with determining that the difference fails to satisfy the predefined criterion, the method causes information regarding the object of interest at the particular location to be collected, such as to permit a map that references the object of interest or other information associated with the object of interest to be updated. | 2022-06-23 |
20220198216 | COMPUTER-READABLE RECORDING MEDIUM STORING IMAGE OUTPUT PROGRAM, IMAGE OUTPUT METHOD, AND IMAGE OUTPUT APPARATUS - A process includes inputting a first image to a machine learning model, acquiring a feature amount of the first image and a first estimation result by the model to which the first image is input, selecting at least one second image from a plurality of images, based on the feature amount, inputting the second image to the model, acquiring a second estimation result by the model to which the second image is input, generating, based on the first image and the first estimation result, a third image that indicates an area of the first image that contributes to the first estimation result more than other areas, generating, based on the second image and the second estimation result, a fourth image that indicates an area of the second image that contributes to the second estimation result more than other areas, and outputting the third image and the fourth image. | 2022-06-23 |
20220198217 | MODEL PARALLEL TRAINING TECHNIQUE FOR NEURAL ARCHITECTURE SEARCH - A model parallel training technique for neural architecture search including the following operations: (i) receiving a plurality of ML (machine learning) models that can be substantially interchangeably applied to a computing task; (ii) for each given ML model of the plurality of ML models: (a) determining how the given ML model should be split for model parallel processing operations, and (b) computing a model parallelism score (MPS) for the given ML model, with the MPS being based on an assumption that the split for the given ML model will be used at runtime; and (iii) selecting a selected ML model based, at least in part, on the MPS scores of the ML models of the plurality of ML models. | 2022-06-23 |
20220198218 | METHODS AND APPARATUS FOR RECOGNIZING PRODUCE CATEGORY, ORGANIC TYPE, AND BAG TYPE IN AN IMAGE USING A CONCURRENT NEURAL NETWORK MODEL - In some embodiments, a method can include capturing images of produce. The method can further include generating simulated images of produce based on the images of produce. The method can further include associating each image of produce from the images of produce and each simulated image of produce from the simulated images of produce with a category indicator, an organic type indicator, and a bag type indicator, to generate a training set. The method can further include training a machine leaning model using the training set such that when the machine learning model is executed, the machine learning model receives an image and generates a predicted category indicator of the image, a predicted organic type indicator of the image, and a predicted bag type indicator of the image. | 2022-06-23 |
20220198219 | MACHINE-LEARNING IMAGE RECOGNITION FOR CLASSIFYING CONDITIONS BASED ON VENTILATORY DATA - The technology relates to methods and systems for recognition of conditions from ventilation data. The methods may include acquiring ventilation data for ventilation of a patient during a time period; generating an image based on the acquired ventilation data; providing, as input into a trained machine learning model, the generated image, wherein the trained machine learning model was trained based on images having a same type as the generated image; and based on output from the trained machine learning model, generating a predicted condition of the patient. The image may be generated by storing ventilatory data as pixel channel values to generate a human-indecipherable image. | 2022-06-23 |
20220198220 | INFORMATION MANAGEMENT APPARATUS, INFORMATION PROCESSING APPARATUS, AND CONTROL METHOD THEREOF - An information management apparatus comprises a communication unit configured to communicate with a plurality of external apparatuses having learning functions, and a control unit configured to control the communication with the plurality of external apparatuses performed by the communication unit. The control unit, if supervisory data generated when a predetermined external apparatus executes a learning function is received from the predetermined external apparatus via the communication unit, selects, from among the plurality of external apparatuses, an external apparatus, other than the predetermined external apparatus, with which the supervisory data is to be shared, and performs control so that the supervisory data is transmitted to the selected external apparatus. | 2022-06-23 |
20220198221 | ARTIFICIAL INTELLIGENCE GENERATED SYNTHETIC IMAGE DATA FOR USE WITH MACHINE LANGUAGE MODELS - A computer completes a data image analysis task. The computer receives a machine learning (ML) model trained for use with image data content characterized by first context. The computer receives an evaluation image dataset having evaluation image data content characterized by a second context. The computer receives a request to complete an image data analysis task for the evaluation image dataset using the ML model. The computer compares the contexts to determine whether the contexts are similar and whether the evaluation image dataset is compatible with the ML model. If the evaluation dataset is incompatible with the ML model, the computer uses the generative model to generate a ML model compatible synthetic image dataset based on the evaluation dataset. The computer applies the ML model to the synthetic image dataset to provide an answer for the data image analysis task; the computer delivers the answer to a user interface. | 2022-06-23 |
20220198222 | AUTOMATED GENERATION OF MACHINE LEARNING MODEL PIPELINE COMBINATIONS - A computer receives a dataset and a set of ML pipeline components to generate a preferred ensemble of Machine Learning (ML) pipelines. An Automated Learning (AutoML) tool is applied to generate a plurality of ML pipelines. A performance value is determined for each pipeline, and a set of candidate pipelines is identified based on the performance values. The candidate pipelines are combined into candidate ensembles. A database provides historic performance data for a plurality of historic ensembles applied to a plurality of historic datasets. A metamodel is trained to identify patterns within the historic performance data, and a applies the patterns to generate predicted ensemble performance values for the candidate ensembles. A preferred ensemble is selected based on the predicted performance value rankings. | 2022-06-23 |
20220198223 | TASK CODE RECOMMENDATION MODEL - Certain aspects of the present disclosure provide techniques for generating a recommendation of task codes for a user of a task management application. A machine learning model is trained on historical data, which includes task code histories of users and corresponding location data of computing devices the user is accessing. The trained model generates a set of predicted task codes and a respective probability indicating the likelihood a user will select the task code. A subset of task codes are identified, for example, that meet or exceed a probability threshold value. The subset of task codes are included in a recommendation displayed in the application to the user. The selection of a task code by a user not only is included in that user's task code history but is also indicative of feedback for the trained model for further training. | 2022-06-23 |
20220198224 | FACE RECOGNITION METHOD, TERMINAL DEVICE USING THE SAME, AND COMPUTER READABLE STORAGE MEDIUM - A backlight face recognition method, a terminal device using the same, and a computer readable storage medium are provided. The method includes: performing a face detection on each original face image in an original face image sample set to obtain a face frame corresponding to the original face image; capturing the corresponding original face images from the original face image sample set, and obtaining a new face image containing background pixels corresponding to the captured original face images from the original face image sample set; preprocessing all the obtained new face images to obtain a backlight sample set and a normal lighting sample set; and training a convolutional neural network using the backlight sample set and the normal lighting sample set until the convolutional neural network reaches a preset stopping condition. The trained convolutional neural network will improve the accuracy of face recognition in complex background and strong light. | 2022-06-23 |
20220198225 | METHOD AND SYSTEM FOR DETERMINING ACTION OF DEVICE FOR GIVEN STATE USING MODEL TRAINED BASED ON RISK-MEASURE PARAMETER - A method of determining an action of a device for a given situation, implemented by a computer system, includes for a learning model that learns a distribution of rewards according to the action of the device for the situation using a risk-measure parameter associated with control of the device, selectively setting a value of the risk-measure parameter in accordance with an environment in which the device is controlled; and determining the action of the device for the given situation when controlling the device in the environment, based on the set value of the risk-measure parameter. | 2022-06-23 |
20220198226 | METHOD AND SYSTEM FOR GENERATING A CENTERLINE FOR AN OBJECT, AND COMPUTER READABLE MEDIUM - Methods and Systems for generating a centerline for an object in an image and computer readable medium are provided. The method includes receiving an image containing the object. The method also includes generating the centerline of the object, by a processor, using a reinforcement learning network configured to predict movement of a virtual agent that traces the centerline in the image. The reinforcement learning network is further configured to perform at least one auxiliary task that detects a bifurcation in a trajectory of the object. The reinforcement learning network is trained by maximizing a cumulative reward and minimizing an auxiliary loss of the at least one auxiliary task. Additionally, the method includes displaying the centerline of the object. | 2022-06-23 |
20220198227 | FORCE SENSOR SAMPLE CLASSIFICATION - A classification system for classifying sensor samples in a sensor system, the sensor system comprising N force sensors each configured to output a sensor signal, where N≥1, each sensor sample comprising N sample values from the N sensor signals, respectively, the classification system comprising: a classifier configured, for each of a series of candidate sensor samples, to perform a classification operation based on the N sample values concerned and generate a classification result which labels the candidate sensor sample as indicative of a defined target event, thereby generating a series of classification results corresponding to the series of candidate sensor samples, respectively; a determiner configured to output at least one event determination based on the series of classification results; and a controller configured to control the classifier and/or the determiner based on one or more controller input signals. | 2022-06-23 |
20220198228 | METHOD FOR DETECTING DEFECTS IN MULTI-SCALE IMAGES AND COMPUTING DEVICE UTILIZING METHOD - A method for detecting defects in multi-scale images and a computing device applying the method acquires a to-be-detected image and converts the to-be-detected image into a plurality of target images of preset sizes. Feature extraction is performed on each target image by using a pre-trained encoder to obtain a latent vector, the latent vector of each target image is inputted into a decoder corresponding to the encoder to obtain a reconstructed image and then into a pre-trained Gaussian mixture model to obtain an estimated probability. Reconstruction error is calculated according to each target image and the corresponding reconstructed image. A total error is calculated according to the reconstruction error of each target image and the corresponding estimated probability, and a detection result is determined according to the total error of each target image and a corresponding preset threshold, thereby improving an accuracy of defect detection. | 2022-06-23 |
20220198229 | SYSTEMS AND METHODS RELATED TO APPLIED ANOMALY DETECTION AND CONTACT CENTER COMPUTING ENVIRONMENTS - A system for detecting anomalies in metric data provided by one or more customers according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to receive metric data indicative of a plurality of time-series based observations for a particular customer metric, to define, based on the metric data, a plurality of parameters to characterize one or more spheres each configured to capture a number of time-series based observations for the particular customer metric, and to generate, based on the plurality of parameters, the one or more spheres to determine coverage of the metric data within the one or more spheres and detect one or more anomalies in the metric data. | 2022-06-23 |
20220198230 | AUXILIARY DETECTION METHOD AND IMAGE RECOGNITION METHOD FOR RIB FRACTURES BASED ON DEEP LEARNING - The present invention relates to the technical field of medical treatment, in particular to an auxiliary detection method and image recognition method for rib fractures based on a deep learning algorithm. The auxiliary detection method comprises the following steps: selecting a certain number of chest CT images as a training set, and labeling a rib fracture area and a rib number in the chest CT images; performing data normalization on the image; training a model by taking the processed image as an input, and the rib fracture area and rib number in the labeled image as an output, wherein the training model comprises a rib detection model, a rib fracture segmentation model, and a rib numbering and sectioning model; and processing the chest CT image to be detected and inputting the processed chest CT image into a trained rib fracture detection model, and outputting a detection result. According to the auxiliary detection method for rib fractures based on the deep learning algorithm provided by the embodiment of the present invention, the cases of false positive and false negative of rib fracture detection are effectively reduced. In addition, this detection result provides position information of a suspected rib fracture, which can assist doctors in diagnosis. | 2022-06-23 |
20220198231 | IMAGING DOCUMENTS - A business method includes imaging documents with an imaging device placed at a location. The imaging device receives imaging requests from users upon payment. Unique lighting schemes notify users of their imaging requests. Payment is split between an entity owning or renting the imaging device and an entity where the imaging device is located. Over a cellular network, toner usage is monitored in the imaging device. Upon the toner level reaching a predetermined low, the entire imaging device is collected from the location and swapped with another imaging device having a toner lever above the low. Workers in the “gig” economy are expected to collect and swap the devices. No longer do users change or swap empty toner cartridges with full or fresh toner cartridges. Similarly, media usage in the imaging device is monitored over the cellular network for replacement of media. Other embodiments are envisioned. | 2022-06-23 |
20220198232 | ACCESS CONTROL FOR ENCRYPTED DATA IN MACHINE-READABLE IDENTIFIERS - A client device collects immunization data includes a type of immunization given to an individual and a date that the immunization was provided to the individual. The client device converts immunization data into a numeric string, where the numeric string as converted comprises an encrypted payload portion and a mode indicator portion. The client device generates a two-dimensional machine-readable identifier using the numeric string. A reader device reads the two-dimensional machine-readable identifier and accesses the numeric string. The reader device converts at least a portion of the numeric string comprising the immunization data into a predetermined format for importing into an electronic health record (EHR). | 2022-06-23 |
20220198233 | Apparatus and Method for Improved Reading of RFID Tags During Manufacture - An Apparatus and Method for reliably sorting RFID chips, in inlays, labels, tags or other units of manufacture, into rows and columns, and using that information to report their exact position on a moving web, in support of further manufacturing processes, in the presence of crosstalk, with speed and accuracy exceeding prior art. | 2022-06-23 |
20220198234 | TRACKING A COLLECTIVE OF OBJECTS - Please substitute the following paragraph(s) for the abstract now appearing in the currently filed specification: | 2022-06-23 |
20220198235 | MANAGEMENT SYSTEM FOR RESTAURANT COLD STORE - The present disclosure discloses a management system for a restaurant cold store. The management system includes RFID tags, an RFID reader, a door opening and closing sensor, and a computer system. Each RFID tag has a unique electronic code. The RFID reader is used for reading data from the RFID tags. The door opening and closing sensor is used for monitoring the state of the door of the cold store to trigger the RFID reader to read the data from the RFID tags based on the determination that the door is closed, so as to automatically trigger a stock count. The computer system stores inventory data of materials in the cold store, and the computer system updates the inventory data according to the data obtained by the RFID reader based on the determination that the door opening and closing sensor detects that the door of the cold store is closed. | 2022-06-23 |
20220198236 | RFID TAG - A Radio Frequency Identification (RFID) tag is disclosed. The RFID tag includes an antenna to receive a high frequency signal, a capacitor bank coupled with the antenna, a charge pump coupled with the antenna configured to convert the high frequency signal to a direct current (DC) signal, an envelope detector to measure peak voltage of the high frequency signal and a detector to compare an output of the charge pump and an output of the envelope detector. The RFID tag also includes an impedance tuning circuit coupled with the charge pump and the envelope detector configured change a capacitance of the capacitor bank based on an output of the detector and the envelope detector. | 2022-06-23 |
20220198237 | DUAL SYSTEM RFID TAG - A Radio Frequency Identification (RFID) tag is disclosed. The RFID tag includes an antenna to receive an input AC signal and a tuning system coupled with the antenna to optimize signal strength of the input AC signal. The tuning system includes a charge pump rectifier. A diode rectifier is included and is coupled with the antenna to receive the input AC signal after the tuning system optimizes the signal strength by tuning input impedance of the antenna. | 2022-06-23 |
20220198238 | RFID TAG - An RFID tag includes a circuit board, an RFID IC and a functional module. The circuit board has an antenna conductor. The RFID IC is mounted on the circuit board. The functional module is connected to the circuit board through a lead wire. An electrical length of a connection wiring that electrically connects the functional module to an element on the circuit board is within ±10% of an integral multiple of a half wavelength of a radio signal that the RFID IC transmits or receives. | 2022-06-23 |
20220198239 | METHOD FOR MANUFACTURING NONCONTACT COMMUNICATION MEDIUM AND NONCONTACT COMMUNICATION MEDIUM - A noncontact communication medium includes a processing circuit that is mounted on a substrate on which an antenna coil is formed, and has an internal capacitor, and an external capacitor that composes a resonance circuit configured to resonate at a predetermined resonance frequency, along with the internal capacitor and the antenna coil. A method for manufacturing a noncontact communication medium includes measuring a temporary resonance frequency in a state in which the external capacitor is not connected to the processing circuit and in a state in which the processing circuit is connected to the antenna coil, and deciding capacitance of the external capacitor based on a degree of difference between a reference resonance frequency in a case where the noncontact communication medium performs communication with an outside through a magnetic field and a temporary resonance frequency. | 2022-06-23 |
20220198240 | NONCONTACT COMMUNICATION MEDIUM - A noncontact communication medium includes an antenna coil that is formed on a substrate having a through-hole and induces power with application of a magnetic field from an outside, and a processing circuit that operates using the power induced by the antenna coil. The processing circuit is inserted in the middle of the antenna coil. The antenna coil is wound in a loop shape along an outer periphery of the substrate. An outer peripheral end of the antenna coil is connected to the through-hole. A portion of the antenna coil on the substrate facing a position of the through-hole has a shape recessed to an inner peripheral side of the antenna coil in a winding direction. | 2022-06-23 |
20220198241 | NONCONTACT COMMUNICATION MEDIUM - A noncontact communication medium comprises an antenna coil that is formed in a substrate and induces power with application of a magnetic field from an outside, and a processing circuit that operates using the power induced by the antenna coil. The substrate has a plurality of layers in a thickness direction. The antenna coil is wound in a loop shape in a first layer among the plurality of layers. One end and the other end of the antenna coil are electrically connected through an auxiliary antenna coil wound in a loop shape in a second layer different from the first layer among the plurality of layers. At least one of the first layer or the second layer is buried in the substrate. | 2022-06-23 |
20220198242 | METHOD AND SYSTEM FOR PREDICTIVE APPLICATION OF VIRTUAL PERSONALITY RENDERINGS - A method and system for predictive application of virtual personality renderings generated from a personality model/profile for an individual depicted in the form of a geometric object that represents the personality profile for the individual. The personality rendering may comprise a virtual shape having a surface area divided into multiple regions, with each region defining a personality trait. The system collects personality datapoints from individuals or representative of the individuals. Each personality datapoint represents a magnitude to which the individual exhibits a personality trait. The personality datapoints are introduced into the base personality model to generate a unique personality rendering. As personality data points are added to base personality model, multiple vectors may project therefrom, causing the base personality model to reconfigure into a non-uniform shape representative of the individual's unique personality. | 2022-06-23 |
20220198243 | PROCESSING DATA FOR A LAYER OF A NEURAL NETWORK - A method of processing input data for a given layer of a neural network using a data processing system comprising compute resources for performing convolutional computations is described. The input data comprises a given set of input feature maps, IFMs, and a given set of filters. The method comprises generating a set of part-IFMs including pluralities of part-IFMs which correspond to respective IFMs, of the given set of IFMs. The method further includes grouping part-IFMs in the set of part-IFMs into a set of selections of part-IFMs. The method further includes convolving, by respective compute resources of the data processing system, the set of selections with the given set of filters to compute a set of part-output feature maps. A data processing system for processing input data for a given layer of a neural network is also described. | 2022-06-23 |
20220198244 | METHOD FOR DIAGNOSING OPEN-CIRCUIT FAULT OF SWITCHING TRANSISTOR OF SINGLE-PHASE HALF-BRIDGE FIVE-LEVEL INVERTER - A method for diagnosing an open-circuit fault of a switching transistor of a single-phase half-bridge five-level inverter is provided. It includes the following steps. A semi-physical experiment platform with a DSP controller and an RT-LAB real-time simulator as its core constructed, and an output side voltage is selected as a fault signal variable. Empirical mode decomposition is used to extract a fault feature vector, and then a HHT time-frequency diagram of the fault feature vector is extracted, a voltage signal is converted into spectrum data, and time-frequency diagram fuzzy sets corresponding to different fault types are obtained. Fusion of the time-frequency diagram fuzzy sets of the same fault type is performed to obtain a fusion image that contains more fault features. The fusion images corresponding to all fault types are inputted into the deep convolutional neural network for training and testing, and a fault diagnosis result is obtained. | 2022-06-23 |
20220198245 | NEUROMORPHIC ALGORITHM FOR RAPID ONLINE LEARNING AND SIGNAL RESTORATION - A computer-implemented method of training a neural network to recognize sensory patterns includes obtaining input data, preprocessing the input data in one or more preprocessors of the neural network, and applying the preprocessed input data to a core portion of the neural network. The core portion of the neural network includes a plurality of principal neurons and a plurality of interneurons, and is configured to implement a feedback loop from the interneurons to the principal neurons that supports persistent unsupervised differentiation of multiple learned sensory patterns over time. The method further includes obtaining an output from the core portion, and performing at least one automated action based at least in part on the output obtained from the core portion. The neural network may be adaptively expanded to facilitate the persistent unsupervised differentiation of multiple learned sensory patterns over time by incorporating additional interneurons into at least the core portion. | 2022-06-23 |
20220198246 | VARIATIONAL ANNEALING - A method, device, and computer-readable medium for solving optimization problems using a variational formulation of classical or quantum annealing. The input states and the parameters of the variational ansatz are initialized, and variational classical or quantum annealing algorithm is applied until a desirable output is obtained. By generalizing the target distribution with a parameterized model, an annealing framework based on the variational principle is used to search for groundstate solutions. Modern autoregressive models such as recurrent neural networks may be used for parameterizations. The method may be implemented on spin glass Hamiltonians. | 2022-06-23 |
20220198247 | NEURAL NETWORK CIRCUIT DEVICE - There is provided a neural network circuit device including a plurality of synapse circuits storing a synaptic coupling weight and a neuron circuit connected to the plurality of synapse circuits. The plurality of synapse circuits store the synaptic coupling weight in a non-volatile manner and output a voltage signal having a magnitude based on the stored synaptic coupling weight in response to an input signal. The neuron circuit includes a neuron MOS transistor having a floating gate and a plurality of control gates which are capacitively coupled to the floating gate and to which the voltage signals from the plurality of synapse circuits are input respectively, and a pulse generator outputting a pulse signal by turning on or off the neuron MOS transistor. | 2022-06-23 |
20220198248 | MERGE OPERATIONS FOR DARTS - A one-shot neural architecture search method referred to as MergeNAS by merging different types of convolutions into a single operation. This mergence approach reduces the search cost to roughly half a GPU-day as well as alleviates the over-fitting problem caused by a traditional differentiable architecture search (DARTS) approach by reducing the number of redundant parameters. | 2022-06-23 |
20220198249 | EXECUTION OF NEURAL NETWORKS - Example techniques for causing execution of neural networks are described. A neural network includes a first part and a second part. A determination is made that a first physical resource in a first computing device is to execute the first part and that a second physical resource in a second computing device is to execute the second part. The determination is based on a latency in communication between the first physical resource and the second physical resource. The first computing device and the second computing device are part of a cluster. | 2022-06-23 |
20220198250 | WEIGHTED MATRIX FOR INPUT DATA STREAM - Examples of performing convolution operations based on a weighted matrix are described. In an example, an input data stream vector is processed using a weighted matrix stored onto a processing unit of a neural network accelerator. The weighted matrix may correspond to a first convolution filter and a second convolution filter. | 2022-06-23 |
20220198251 | SEMICONDUCTOR DEVICE AND METHOD OF DRIVING THE SAME - A semiconductor device includes variable resistance elements on a semiconductor substrate. Each of the variable resistance elements includes a first electrode, a second electrode, and a variable resistance layer that is sandwiched between the first electrode and the second electrode and that stores a resistance value that is continuously variable. The variable resistance layer includes a filament whose shape differs according to a neural network weight, and stores, as an analog value, the resistance value that is variable. | 2022-06-23 |
20220198252 | STDP WITH SYNAPTIC FATIGUE FOR LEARNING OF SPIKE-TIME-CODED PATTERNS IN THE PRESENCE OF PARALLEL RATE-CODING - A circuit implementing a spiking neural network that includes a learning component that can learn from temporal correlations in the spikes regardless of correlations in the rates. In some embodiments, the learning component comprises a rate-discounting component. In some embodiments, the learning rule computes a rate-normalized covariance (normcov) matrix, detects clusters in this matrix, and sets the synaptic weights according to these clusters. In some embodiments, a synapse with a long-term plasticity rule has an efficacy that is composed by a weight and a fatiguing component. In some embodiments, A Hebbian plasticity component modifies the weight component and a short-term fatigue plasticity component modifies the fatiguing component. The fatigue component increases with increases in the presynaptic spike rate. In some embodiments, the fatigue component increases are implemented in a spike-based manner. In some embodiments, the Hebbian plasticity is a spike-timing-dependent plasticity (STDP), resulting in a fatiguing STDP (FSTDP) synapse. | 2022-06-23 |
20220198253 | Deep Learning-based Online Adaptation of Digital Pre-Distortion and Power Amplifier Systems - An auto-tuning controller for improving a performance of a power amplifier system is provided. The controller includes an interface including input terminals and output terminals, the interface being configured to acquire input signal conditions of power amplifiers (PAs), a training circuit including a processor and a memory running and storing a Digital Doherty amplifier (DDA) controller (module), a DPD controller (module) and a DDA-DPD neural network (NN). The training circuit is configured to perform sampling the input signal conditions, and selecting a DPD model from a set of polynomial models for the DPD controller and a set of DDA optimization variables for the DDA controller, using optimized DPD model and DDA coefficients, wherein the optimized DPD model and DDA coefficients are provided by performing an offline optimization for the DPD model and DDA coefficients based on a predetermined optimization method, collecting the optimized DPD coefficients and optimized DDA optimization variables, generating online-DDA optimal coefficients and DPD optimal coefficients using a trained DDA-DPD NN, and updating the generated optimal DDA and DPD coefficients via the output terminals of the interface. | 2022-06-23 |
20220198254 | EXPLAINABLE TRANSDUCER TRANSFORMERS - An explainable transducer transformer (XTT) may be a finite state transducer, together with an Explainable Transformer. Variants of the XTT may include an explainable Transformer-Encoder and an explainable Transformer-Decoder. An exemplary Explainable Transducer may be used as a partial replacement in trained Explainable Neural Network (XNN) architectures or logically equivalent architectures. An Explainable Transformer may replace black-box model components of a Transformer with white-box model equivalents, in both the sub-layers of the encoder and decoder layers of the Transformer. XTTs may utilize an Explanation and Interpretation Generation System (EIGS), to generate explanations and filter such explanations to produce an interpretation of the answer, explanation, and its justification. | 2022-06-23 |
20220198255 | TRAINING A SEMANTIC PARSER USING ACTION TEMPLATES - Methods and systems for training a semantic parser includes performing an automated intervention action in a text-based environment. An inverse action is performed in the text-based environment to reverse the intervention action. States of the text-based environment are recorded before and after the intervention action and the inverse action. The recorded states are evaluated to generate training data. A semantic parser neural network model is trained using the training data. | 2022-06-23 |
20220198256 | ARTIFICIAL INTELLIGENCE BASED OPERATIONS IN ENTERPRISE APPLICATION - The present invention provides a system and method for managing operations in an enterprise application. The invention includes predicting a dataset characteristic such as an incident or outage in the enterprise application based on analysis of the dataset received from distinct data sources. The invention includes data cleansing, feature extraction based on probability data analysis and classification of dataset based on data models trained on historical dataset characteristic data. The invention includes linkedchain based architecture with configurable components structuring the enterprise application. | 2022-06-23 |
20220198257 | ARCHITECTURE FOR RUNNING CONVOLUTIONAL NETWORKS ON MEMORY AND MIPS CONSTRAINED EMBEDDED DEVICES - This disclosure describes techniques to perform convolutional neural networks (CNNs) on embedded devices. The techniques include operations comprising: accessing DNN information including definition of layers and weights of the DNN; obtaining cache or memory information for one or more cache or memory levels of the resource constrained embedded device; and configuring the DNN to be loaded onto the one or more cache or memory levels of the resource constrained embedded device based on the cache or memory information and the DNN information. | 2022-06-23 |
20220198258 | Saliency Prioritization for Image Processing - According to one implementation, a system includes a computing platform having a hardware processor and a system memory storing a software code including a trained neural network (NN). The hardware processor executes the software code to receive an input image including a pixel anomaly, identify, using the trained NN, one or more salient regions of the input image, and determine whether the pixel anomaly is located inside any of the one or more salient regions. The hardware processor further executes the software code to assign a first priority to the pixel anomaly when it is determined that the pixel anomaly is located inside any of the one or more salient regions, and to assign a second priority, lower than the first priority, to the pixel anomaly when it is determined that the pixel anomaly is not located inside any of the one or more salient regions. | 2022-06-23 |
20220198259 | MULTIDIMENSIONAL DATA ANALYSIS FOR ISSUE PREDICTION - A system for issue prediction based on multidimensional data analysis includes a model generator that receives a resolved data item relating to a service issue. The resolved data item includes different attributes corresponding to multiple data dimensions and adjusts a population of attributes based on a statistical data model and a deep learning data model operating independent of each other. The statistical data model operates on the attributes for providing a predictive feature and the deep learning data model operates on the attributes for providing a predictive label based on performance metrics related to the data dimensions. The predictive feature and the predictive label collectively define training data. The model generator also trains a classification model based on the training data for predicting a potential issue related to an unresolved data item. The trained data model provides a trigger based on the potential issue being related to the performance metrics. | 2022-06-23 |
20220198260 | MULTI-LEVEL MULTI-OBJECTIVE AUTOMATED MACHINE LEARNING - Multi-level objectives improve efficiency of multi-objective automated machine learning. A hyperband framework is established with a kernel density estimator to shrink the search space based on evaluation of lower-level objectives. A Gaussian prior assumption directly shrinks the search space to find a main objective. | 2022-06-23 |
20220198261 | ARTIFICIAL INTELLIGENCE VIA HARDWARE-ASSISTED TOURNAMENT - A system and method for providing for adoption of solvers for solving at least one task is disclosed. The system and method include a controller, solvers capable of solving the at least one task, and at least one memory. The controller admits ones of the solvers into a competition for solving the at least one task, provides, via the at least one memory, an input of the task to the admitted solvers, provides, via the at least one memory, intermediate results of execution by the admitted solvers that are provided the input, receives a prediction of the next intermediate result from the admitted solvers predicting from at least one of the provided input and received intermediate results, and ranks the at least one of the admitted solvers for solving the task based on at least one of the next intermediate results, the provided input and received intermediate results. | 2022-06-23 |
20220198262 | METHOD, APPARATUS, AND COMPUTER PROGRAM PRODUCT FOR SURVEILLANCE OF ROAD ENVIRONMENTS VIA DEEP LEARNING - A method, apparatus and computer program product are provided for surveillance of road environments via deep learning. In this regard, one or more features for vehicle sensor data associated with one or more vehicles traveling along a road segment proximate to a vehicle are determined. The vehicle includes one or more sensors that captures the vehicle sensor data. Furthermore, vehicle behavior data associated with the one or more vehicles is predicted using a machine learning model that receives the one or more features. The machine learning model is trained for detection of vehicle behavior based on historical vehicle sensor data and one or more rules associated with the road segment. The vehicle behavior data is also encoded in a database to facilitate modeling of vehicle behavior associated with the road segment. | 2022-06-23 |
20220198263 | TIME SERIES ANOMALY DETECTION - In an example embodiment, a machine-learned model is trained to specifically identify anomaly points in time series data. The model is capable of being applied in parallel to many different time series simultaneously, allowing for a scalable solution for large scale online networks. The model classifies each data point in a specified time window and outputs rich contextual information for downstream applications, such as ranking and display of the anomalous data points. | 2022-06-23 |
20220198264 | TIME SERIES ANOMALY RANKING - In an example embodiment, a machine-learned model is trained to rank anomaly points in time series data. The model is capable of being applied in parallel to many different time series simultaneously, allowing for a scalable solution for large scale online networks. The model outputs a ranking score for an input anomaly and allows for ranking of anomalies not just in the same time series but anomalies across multiple time series as well. This ranking can then be used to determine how best to present the ranked anomalies to users in a graphical user interface. | 2022-06-23 |
20220198265 | PATTERN DISCOVERY, PREDICTION AND CAUSAL EFFECT ESTIMATION IN TREATMENT DISCONTINUATION - With a trained, computerized discontinuation predictor machine learning component (MLC), predict, based on an input time series, a time when a subject will discontinue a course of medical treatment; with a trained, computerized pattern behavior extractor MLC, extract from said input time series the top k discriminatory sequences via discriminatory sub-sequence mining (said top k discriminatory sequences differentiate between first and second classes of interest to provide a hypothesis for downstream analysis of a cause of discontinuing said course of treatment). With a trained, causal effect estimator computerized MLC, determine a reason why said subject will discontinue said course of medical treatment, based on said top k discriminatory sequences and additional data; and with a computerized user interface, provide said time and said reason why to a responsible party to initiate an intervention. | 2022-06-23 |
20220198266 | USING DISENTANGLED LEARNING TO TRAIN AN INTERPRETABLE DEEP LEARNING MODEL - A method and system of training an interpretable deep learning model includes receiving an input set of data, which may be complex. The input set of data is provided to deep learning model for feature extraction. In an exemplary embodiment, the deep learning model generates a disentangled latent space of features from the feature extraction. The features may comprise semantically meaningful data which is then provided to a low-complexity learning model. The low-complexity learning model generates output based on a specified task (for example, classification or regression). Being a low-complexity learning model provides confidence that the data output from the deep learning model is inherently interpretable. | 2022-06-23 |
20220198267 | APPARATUS AND METHOD FOR ANOMALY DETECTION USING WEIGHTED AUTOENCODER - Apparatus and method to detect anomalies in observations use a first plurality of observations regarding operation of a computing system, which are binned based on features values of the observations. Based on the binning, a weighting score is determined for the observations, which is applied to a loss function of an autoencoder. A second plurality of observations is then applied to the autoencoder as input to determine a reconstruction error value for each observation of the second plurality of observations. The reconstruction error values are used to detect anomalous observations of the second plurality of observations. | 2022-06-23 |
20220198268 | ESTIMATED ONLINE HARD NEGATIVE MINING VIA PROBABILISTIC SELECTION AND SCORES HISTORY CONSIDERATION - According to one embodiment, a method, computer system, and computer program product for hard negative training is provided. The embodiment may include a computer receiving a training set, where the training set comprises one or more training samples. The computer trains a deep neural network (DNN) with the training set. The embodiment may also include determining, using the DNN, information for each of the one or more training samples, where the information includes one or more scores associated with the one or more training samples. The embodiment may further include generating a training epoch from the one or more training samples based on the information and updates the information based on using the training epoch with the DNN. | 2022-06-23 |
20220198269 | BIG AUTOMATION CODE - A system and method to apply deep learning techniques to an automation engineering environment are provided. Big code files and automation coding files are retrieved by the system from public repositories and private sources, respectively. The big code files include examples general software structure examples to be utilized by the method and system to train advanced automation engineering software. The system represents the coding files in a common space as embedded graphs which a neural network of the system uses to learn patterns. Based on the learning, the system can predict patterns in the automation coding files. From the predicted patterns executable automation code may be created to augment the existing automation coding files. | 2022-06-23 |
20220198270 | NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS - A neural network model training method and apparatus are provided. The method includes a first training operation of training the neural network model with original data, the first training operation including generating a first feature map for the original data, and generating a first class activation map for the original data from the generated first feature map, and a second training operation of training the neural network model with adversarial data transformed from the original data, the second training operation including generating a second feature map for the adversarial data, generating a second class activation map for the adversarial data from the generated second feature map, and training the neural network model so that the second class activation map follows the first class activation map based on logit pairing for the first and second class activation maps. | 2022-06-23 |
20220198271 | METHOD FOR BUILDING A RESOURCE-FRUGAL NEURAL NETWORK - A method for building a neural network configured to be run on a destination computing unit is implemented by a system including a computer and a memory storing a learning dataset. The method includes providing a neural network having an initial topology, and training the initial topology over the learning dataset. The topology of the neural network is optimized, which includes at least one iteration of the following steps: for each of a plurality of candidate topological changes, estimating the variation induced by the candidate topological change on: the neural network's error, and a value of at least one physical quantity needed for executing the neural network on the destination processing unit, selecting at least one of the candidate topological changes based on said estimation and updating the topology of the neural network according to said selected topological change, and training the updated neural network over the learning dataset. | 2022-06-23 |
20220198272 | SYSTEM AND METHOD FOR DOMAIN SPECIFIC NEURAL NETWORK PRUNING - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for domain-specific pruning of neural networks are described. An exemplary method includes obtaining a first neural network trained based on a first training dataset; obtaining one or more second training datasets respectively from one or more domains; and training, based on the first neural network and the one or more second training datasets, a second neural network comprising the first neural network and one or more branches extended from the first neural network, wherein the second neural network is applicable for inferencing in the one or more domains, and the training comprises: training the one or more branches based respectively on the one or more second training datasets and an output of the first neural network. | 2022-06-23 |
20220198273 | ASYNCHRONOUS AGENTS WITH LEARNING COACHES AND STRUCTURALLY MODIFYING DEEP NEURAL NETWORKS WITHOUT PERFORMANCE DEGRADATION - Methods and computer systems improve a trained base deep neural network by structurally changing the base deep neural network to create an updated deep neural network, such that the updated deep neural network has no degradation in performance relative to the base deep neural network on the training data. The updated deep neural network is subsequently training. Also, an asynchronous agent for use in a machine learning system comprises a second machine learning system ML2 that is to be trained to perform some machine learning task. The asynchronous agent further comprises a learning coach LC and an optional data selector machine learning system DS. The purpose of the data selection machine learning system DS is to make the second stage machine learning system ML2 more efficient in its learning (by selecting a set of training data that is smaller but sufficient) and/or more effective (by selecting a set of training data that is focused on an important task). The learning coach LC is a machine learning system that assists the learning of the DS and ML2. Multiple asynchronous agents could also be in communication with each others, each trained and grown asynchronously under the guidance of their respective learning coaches to perform different tasks. | 2022-06-23 |
20220198274 | METHOD AND SYSTEM FOR UNSTRUCTURED INFORMATION ANALYSIS USING A PIPELINE OF ML ALGORITHMS - A system and a method for increasing the classification confidence, with lesser dependence on large sets of training data, obtained by one or more machine learning based algorithms, by analyzing unstructured information using unstructured analysis pipeline comprising a probabilistic network such as a Bayesian network. The probabilistic network may comprise nodes associated with elements and cues defined by experts, and require fewer labelled data samples to train. The confidence level of the elements may be determined by machine learning and unstructured analysis methods and processed by the probabilistic network to estimate the confidence for a characterization quantity. | 2022-06-23 |
20220198275 | CONTROLLING DISTRIBUTION OF TRAINING DATA TO MEMBERS OF AN ENSEMBLE - A machine learning system includes a coach machine learning system that uses machine learning to help a student machine learning system learn its system. By monitoring the student learning system, the coach machine learning system can learn (through machine learning techniques) “hyperparameters” for the student learning system that control the machine learning process for the student learning system. The machine learning coach could also determine structural modifications for the student learning system architecture. The learning coach can also control data flow to the student learning system. | 2022-06-23 |
20220198276 | METHOD AND PLATFORM FOR PRE-TRAINED LANGUAGE MODEL AUTOMATIC COMPRESSION BASED ON MULTILEVEL KNOWLEDGE DISTILLATION - Disclosed are an automatic compression method and platform for a pre-trained language model based on multilevel knowledge distillation. The method includes the following steps: step 1, constructing multilevel knowledge distillation, and distilling a knowledge structure of a large model at three different levels: a self-attention unit, a hidden layer state and an embedded layer; step 2, training a knowledge distillation network of meta-learning to generate a general compression architecture of a plurality of pre-trained language models; and step 3, searching for an optimal compression structure based on an evolutionary algorithm. Firstly, the knowledge distillation based on meta-learning is studied to generate the general compression architecture of the plurality of pre-trained language models; and secondly, on the basis of a trained meta-learning network, the optimal compression structure is searched for via the evolutionary algorithm, so as to obtain an optimal general compression architecture of the pre-trained language model independent of tasks. | 2022-06-23 |
20220198277 | POST-HOC EXPLANATION OF MACHINE LEARNING MODELS USING GENERATIVE ADVERSARIAL NETWORKS - Herein are generative adversarial networks to ensure realistic local samples and surrogate models to provide machine learning (ML) explainability (MLX). Based on many features, an embodiment trains an ML model. The ML model inferences an original inference for original feature values respectively for many features. Based on the same features, a generator model is trained to generate realistic local samples that are distinct combinations of feature values for the features. A surrogate model is trained based on the generator model and based on the original inference by the ML model and/or the original feature values that the original inference is based on. Based on the surrogate model, the ML model is explained. The local samples may be weighted based on semantic similarity to the original feature values, which may facilitate training the surrogate model and/or ranking the relative importance of the features. Local sample weighting may be based on populating a random forest with the local samples. | 2022-06-23 |
20220198278 | SYSTEM FOR CONTINUOUS UPDATE OF ADVECTION-DIFFUSION MODELS WITH ADVERSARIAL NETWORKS - A computing device configured for automatic selection of model parameters includes a processor and a memory coupled to the processor. The memory stores instructions to cause the processor to perform acts including providing an initial set of model parameters and initial condition information to a model based on historical data. A model generates data based on the model parameters and the initial condition information. After determining whether the model-generated data is similar to an observed data, updated model parameters are selected for input to the model based on the determined similarity. | 2022-06-23 |
20220198279 | Data-Driven Methodology for Automatic Detection of Data Drift - A system and method for drift detection is disclosed. The method may comprise training and testing an autoencoder, and using the trained and tested autoencoder to automatically detect data drift. The training may include initializing the autoencoder and training the autoencoder based on a first set of sensor data. The testing of the autoencoder with a second set of sensor data may comprise: for an empirical distribution of the reconstruction errors of the second set of sensor data, determining a value of a reconstruction error at the percentile threshold; determining that data drift is not present when the reconstruction error of the second set of sensor data is less than a threshold; and calculating a deviation output for at least one of the one or more sensors. Using the trained and tested autoencoder to automatically detect data drift in sensor data. | 2022-06-23 |
20220198280 | NOVELTY DETECTION USING DEEP LEARNING NEURAL NETWORK - The disclosed technology generally relates to novelty detection and more particularly to novelty detection methods using a deep learning neural network and apparatuses and non-transitory computer-readable media configured for performing the methods. In one aspect, a method for detecting novelty using a deep learning neural network model comprises providing a deep learning neural network model. The deep learning neural network model comprises an encoder comprising a plurality of encoder layers and a decoder comprising a plurality of decoder layers. The method additionally comprises feeding a first input into the encoder and successively processing the first input through the plurality of encoder layers to generate a first encoded input, wherein successively processing the first input comprises generating a first intermediate encoded input from one of the encoder layers prior to generating the first encoded input. The method additionally comprises feeding the first encoded input from the encoder into the decoder and successively processing the first encoded input through the plurality of decoder layers to generate a first reconstructed output. The method additionally comprises feeding the first reconstructed output from the decoder as a second or subsequent input into the encoder and successively processing the first reconstructed output through the plurality of encoder layers, wherein successively processing the first reconstructed output comprises generating a second intermediate encoded input from the one of the encoder layers. The method further comprises detecting a novelty of the original input based on a comparison of the first intermediate encoded input and the second intermediate encoded input. | 2022-06-23 |
20220198281 | JOINT EXECUTION OF DECISION TREE NODES FOR ACCELERATING INFERENCES - An approach of accelerating inferences based on decision trees based on accessing one or more decision trees, wherein each decision tree of the decision trees accessed comprises decision tree nodes, including nodes grouped into one or more supersets of nodes designed for joint execution. For each decision tree of the decision trees accessed, the nodes are executed to obtain an outcome for the one or more decision trees, respectively. For each superset of the one or more supersets of said each decision tree, the nodes of each superset are jointly executed by: loading attributes of the nodes of each superset in a respective cache line of the cache memory processing said attributes from the respective cache line until an inference result is returned based on the one or more outcomes. | 2022-06-23 |