45th week of 2020 patent applcation highlights part 45 |
Patent application number | Title | Published |
20200349356 | SYSTEM AND METHOD OF PROVIDING RECOMMENDATIONS OF MOMENTS OF INTEREST WITHIN VIDEO CLIPS POST CAPTURE - Users desiring to generate videos from video clips may want to locate moments of interest within the video clips. A system and method described herein may be configured to provide recommendations of moments of interest within video clips post capture of the video clips. User accounts associated with users of the system may include preference information that defines user preferences with respect to values of attributes of video clips. Moments of interest may be identified within individual video clips when the individual video clips have at least one value of at least one attribute specified by the user preferences. Recommendations of identified moments of interest may be provide to users. | 2020-11-05 |
20200349357 | METHOD OF CREATING A TEMPLATE OF ORIGINAL VIDEO CONTENT - There is disclosed a method of creating a template of original video content, which is performed on a computer device that has access to a previously generated database of original video content. The method comprises receiving identifiers for at least a portion of an original video content; extracting at least a portion of metadata of the original video content; extracting at least a portion of frames from a sequence of frames of the original video content; identifying a sequence of scenes; creating a vector of the sequence of scenes; generating a template of the original video content that includes at least the portion of the metadata, and a vector of the sequence of scenes of the original video content; and storing the template in a database. | 2020-11-05 |
20200349358 | METHOD AND APPARATUS FOR DETECTING SUSPICIOUS ACTIVITY USING VIDEO ANALYSIS - A system detects a transaction outcome by obtaining video data associated with a transaction area and analyzing the video data to obtain at least one video transaction parameter concerning transactions associated with the transaction area. The transaction area can be a video count of items indicated in the video data as detected by an automated item detection algorithm applied to the video data. The system obtains at least one expected transaction parameter concerning an expected transaction that occurs in the transaction area, such as a scan count of items scanned at a point of sale terminal. The system automatically compares the video transaction parameter(s) to the expected transaction parameter(s) to identify a transaction outcome that may indicate fraudulent activity such as sweethearting in a retail environment. | 2020-11-05 |
20200349359 | DYNAMIC WORKSTATION ASSIGNMENT - Technologies are generally described for adjustment of displayed content based on recognition of viewer. In some examples, content that may include data, as well as, control elements associated with functionality of a surveillance system. The content may be displayed to a viewer based on the viewer's credentials. Responsive to detection of another viewer, the displayed content may be modified based on credentials of the other viewer. Viewers may be detected through a variety of techniques and displayed content may be associated with different authority levels. In other examples, content may be blocked from display if a viewer in a restricted list is detected in view of a display device. | 2020-11-05 |
20200349360 | POPULATION DENSITY DETERMINATION FROM MULTI-CAMERA SOURCED IMAGERY - A method for determining population density of a defined space from multi-camera sourced imagery includes loading a set of images acquired from multiple different cameras positioned about the defined space, locating different individuals within each of the images and computing a population distribution of the located different individuals in respect to different locations of the defined space. The method additionally includes submitting each of the images to a convolutional neural network as training data, each in association with a correspondingly computed population distribution. Subsequent to the submission, contemporaneous imagery from the different cameras is acquired in real time and submitted to the neural network, in response to which, a predicted population distribution for the defined space is received from the neural network. Finally, a message is displayed that includes information correlating at least a portion of the population distribution with a specific location of the defined space. | 2020-11-05 |
20200349361 | FLEXIBLE HARDWARE DESIGN FOR CAMERA CALIBRATION AND IMAGE PRE-PROCESING IN AUTONOMOUS DRIVING VEHICLES - Flexible hardware designs for camera calibration and image pre-processing are disclosed for vehicles including autonomous driving (AD) vehicles. For one example, a sensor unit includes a sensor interface, host interface, and pre-processing hardware. The sensor interface is coupled to a plurality of cameras configured to capture images around an autonomous driving vehicle (ADV). The host interface is coupled to a perception and planning system. The pre-processing hardware is coupled to the sensor interface to receive images from the plurality of cameras and to perform one or more pre-processing functions on the images and to transmit pre-processed images to the perception and planning system via the host interface. The perception and planning system is configured to perceive a driving environment surrounding the ADV based on the pre-processed images and to plan a path to control the ADV to navigate through the driving environment. The pre-processing functions can adjust for different calibrations and formats across the plurality of cameras. | 2020-11-05 |
20200349362 | Method of Computer Vision Based Localisation and Navigation and System for Performing the Same - In relation to the field of vehicle navigation, we describe a method of determining a position of a subject (such as a vehicle, platform or target), comprising the steps of obtaining and storing an object dataset comprising object data indicative of one or more objects in an environment, including an indication of object parameters associated with the or each object, the object parameters including one or more of location, orientation, one or more dimensions, and a type associated with the object, obtaining environment data indicative of a region of the environment from a sensor associated with the subject, determining the presence of an observed object in the environment data, including determining one or more equivalent observed object parameters associated with the observed object, and determining the position of the subject based on a comparison of the observed object parameters with the equivalent object parameters of the objects in the object dataset. | 2020-11-05 |
20200349363 | METHOD AND SYSTEM FOR ESTIMATING LANE LINES IN VEHICLE ADVANCED DRIVER ASSISTANCE DRIVER ASSISTANCE SYSTEMS - An advanced driver assistance system (ADAS) of a vehicle and associated method is disclosed. A first set of sensed lane measurements from a first imaging device and a second set of sensed lane measurements from a second imaging device are obtained. Each of the first and second sets of sensed lane measurements includes a lane estimate for the lane lines on a roadway. Each lane estimate is associated with one lane line. For each lane line, the associated lane estimates from the first and second sets of sensed lane measurements are fused to obtain a fused lane estimate, from which a representative model lane estimate is determined. For each of the plurality of lane lines, the associated lane estimates from the first and second sets of sensed lane measurements and the representative model lane estimate are fused to obtain a corrected fused lane estimate, which is output. | 2020-11-05 |
20200349364 | METHOD AND APPARATUS FOR TRAINING LANE LINE IDENTIFYING MODEL, DEVICE, AND STORAGE MEDIUM - Embodiments of the present disclosure provide a method and apparatus for training a lane line identifying model. The method includes: acquiring a first image of a lane line, the first image being generated using a generating model based on a second image of the lane line, the first image and the second image of the lane line being associated with different physical environments respectively; acquiring lane line information in the second image of the lane line; and training the lane line identifying model using the first image and the acquired lane line information of the lane line. | 2020-11-05 |
20200349365 | DIRECT VEHICLE DETECTION AS 3D BOUNDING BOXES USING NEURAL NETWORK IMAGE PROCESSING - Systems and methods of detecting and tracking one or more vehicles in a field of view of an imaging system using neural network processing. An electronic controller receives an input image from a camera mounted on the host vehicle. The electronic controller applies a neural network configured to output a definition of a three-dimensional bounding box based at least in part on the input image. The three-dimensional bounding box indicates a size and a position of a detected vehicle in a field of view of the input image. The three-dimensional bounding box includes a first quadrilateral shape outlining a rear or front of the detected vehicle and a second quadrilateral shape outline a side of the detected vehicle. | 2020-11-05 |
20200349366 | ONBOARD ENVIRONMENT RECOGNITION DEVICE - The purpose of the present invention is to provide an onboard environment recognition device exhibiting high accuracy of measurement in a wider range of view fields. The present invention pertains to an onboard environment recognition device ( | 2020-11-05 |
20200349367 | IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND PROGRAM - The present disclosure relates to an image processing device, an image processing method, and a program that can make it easier to check a surrounding situation. A viewpoint determination part determines a viewpoint of a viewpoint image related to periphery of a moving object in a case where the moving object is viewed from a predetermined viewpoint, according to a speed of a vehicle that can move at an arbitrary speed. Then, an image synthesis part synthesizes an illustrative image of the vehicle at a position where the vehicle can exist in the captured image of the periphery of the vehicle, and a projection conversion part performs projection conversion on an image obtained by the image synthesis part synthesizing the illustrative image of the vehicle to generate the viewpoint image that is a view from the viewpoint determined by the viewpoint determination part. The present technology can be applied to, for example, an image processing device mounted on a vehicle. | 2020-11-05 |
20200349368 | Enhanced Navigation Instructions with Landmarks Under Difficult Driving Conditions - The technology relates to factors regarding the external environment around a vehicle that are used to trigger enhanced driving directions for use by the driver. The factors can include issues such as adverse weather conditions, low light conditions and temporary obstacles or other obstructions that may prevent or reduce the ability of the driver to see street signs or other landmarks that are part of an initial set of driving directions. Upon determination of one or more relevant factors, the system is able to modify or otherwise enhances directions in real time. This allows the driver to be able to quickly and easily identify other visible landmarks and use such information to navigate to a desired destination. This approach employs one or more on-board cameras configured to detect objects and conditions in the environment adjacent to or otherwise nearby the vehicle, such as within line of sight of the vehicle's front end. | 2020-11-05 |
20200349369 | METHOD AND APPARATUS FOR TRAINING TRAFFIC SIGN IDENFICATION MODEL, AND METHOD AND APPARATUS FOR IDENTIFYING TRAFFIC SIGN - Embodiments of the present disclosure relate to a method and apparatus for training a traffic sign identification model, and a method and apparatus for identifying a traffic sign. The method for training a traffic sign identification model includes: obtaining an original image containing a traffic sign; generating a target image based on the original image through a machine learning model, in which the machine learning model is trained based on a plurality of pairs of sample images, each pair contains an original sample image containing the traffic sign and a modified sample image after modifying the original sample image; and training the traffic sign identification model based at least on the target image. | 2020-11-05 |
20200349370 | METHODS AND SYSTEMS FOR AUTOMATICALLY PREDICTING THE REPAIR COSTS OF A DAMAGED VEHICLE FROM IMAGES - A system and computer-implemented method for automatically predicting the labor, hours, and parts costs for repair of a vehicle includes receiving one or more images of the vehicle from a policyholder. A damage assessment model is accessed. The damage assessment model corresponds to features of vehicle damage based on a plurality of damaged vehicle images contained in an image training database. The damage assessment model is compared to the images of the vehicle and vehicle damage is identified based on the images. In addition, in response to identifying the vehicle damage, total labor costs, total parts costs, and total hours for repair of the vehicle are predicted based on the associated total labor costs, total parts costs, and total hours for repair data contained in the historical claims database. | 2020-11-05 |
20200349371 | SYSTEM AND METHODS OF MONITORING DRIVER BEHAVIOR FOR VEHICULAR FLEET MANAGEMENT IN A FLEET OF VEHICLES USING DRIVER-FACING IMAGING DEVICE - Systems and methods monitor driver behavior for vehicular fleet management in a fleet of vehicles using driver-facing imaging device. The systems and methods herein relate generally to vehicular fleet management for enhancing safety of the fleet and improving the performance of the fleet drivers, and further relate to monitoring the operation of fleet vehicles using one or more driver-facing imaging devices disposed in the fleet vehicles for recording activities of the fleet drivers and their passengers, storing information relating to the monitored activities, selectively generating warnings related to the monitored activities, and reporting the monitored activities to a central fleet management system for use in enhancing the safety of the vehicles of the fleet and for helping to improve the performance of the fleet drivers. | 2020-11-05 |
20200349372 | METHOD AND APPARATUS WITH LIVENESS DETECTION - A liveness detection method and apparatus, and a facial verification method and apparatus are disclosed. The liveness detection method includes detecting a face region in an input image, measuring characteristic information of the face region, adjusting the measured characteristic information in response to the characteristic information not satisfying a condition, and performing a liveness detection on the face region with the adjusted characteristic information upon the measured characteristic information not satisfying the condition. | 2020-11-05 |
20200349373 | Face Recognition System - A face recognition system is provided. The face recognition system includes an electronic device and terminal server. The electronic device comprising: a camera, exposed outside the electronic device; and a scanning unit, scanning a user face through the camera to obtain a user face feature data. The terminal server communicated with the electronic device, comprising: a two-dimensional code generation unit, generating a user two-dimensional code according to the user face feature data; a two-dimensional code database, comprising a plurality of member two-dimensional codes; and a comparison unit, comparing the user two-dimensional code with each of the member two-dimensional codes. | 2020-11-05 |
20200349374 | Systems and Methods for Face Recognition - A system for face recognition includes a subsystem, e.g., an autoencoder, for determining whether an image from which a face is to be recognized is of an acceptable or good quality and whether the image includes a face. A subsystem for recognizing the face in an image may be trained using not only good quality images but also some poor quality images that may or may not include a face. | 2020-11-05 |
20200349375 | Sensing Apparatus and Method - A method comprises positioning a display screen of a mobile device and a surface of interest such that the display screen of the mobile device faces the surface of interest; emitting light by the display screen, wherein at least part of the emitted light is reflected by the surface of interest; receiving, by a camera of the mobile device, at least part of the light emitted by the display screen and reflected from the surface of interest thereby to generate at least one image; and processing the at least one image to determine at least one property of the surface of interest. | 2020-11-05 |
20200349376 | PRIVACY AUGMENTATION USING COUNTER RECOGNITION - Techniques and systems are provided for performing one or more counter recognition techniques. For example, an incident signal can be received by a user device, and one or more signal parameters of the incident signal can be determined. Based on the one or more signal parameters of the incident signal, one or more response signals can be transmitted to prevent object recognition (e.g., face recognition) of a user by the camera. | 2020-11-05 |
20200349377 | METHOD AND SYSTEM FOR TESTING WEARABLE DEVICE - Disclosed are a method and system for testing a wearable device. The method includes: performing an angle acquisition process for at least two times, and calculating an optical imaging parameter value of a target virtual image on the basis of angle variation values acquired in the at least two angle acquisition processes. With the method and system according to the present disclosure, the finally calculated optical imaging parameter value is more objective and more accurate than that acquired by means of the human eyes. | 2020-11-05 |
20200349378 | Data Processing - A data processing device comprises an analyser to analyse successive images captured by a camera and to detect an optically detectable marker in the captured images, a first location detector to detect a location of the optically detectable marker with respect to a location of the camera according to a first detection mode and to generate a first detection result, a second location detector to detect the location of the optically detectable marker with respect to the location of the camera according to a second detection mode different to the first detection mode and to generate a second detection result, and a processor to select at least one of the first detection result and the second detection result and to generate data indicative of the location of the optically detectable marker with respect to the location of the camera based on the selection. | 2020-11-05 |
20200349379 | AUTOMATED AUTHENTICATION REGION LOCALIZATION AND CAPTURE - A device includes a processor, a machine-readable memory, and an optical capture device coupled to the processor. The machine-readable memory, which is accessible to the processor, stores processor-executable instructions and data. The processor is configured to perform certain operations responsive to execution of the processor-executable instructions. The certain operations include capturing image data of a first region of a physical object using the optical capture device. The captured image data includes an anchor region. The certain operations also include determining whether the captured image data at least meets a predetermined level of image quality, and in a case that it does, locating an authentication region in the captured image data based on the anchor region. The certain operations also include authenticating the object based on the captured image data in the authentication region, generating a result of the authenticating, and outputting the result to a user interface of the mobile device. | 2020-11-05 |
20200349380 | ASYMMETRICAL LICENSE PLATE READING (ALPR) CAMERA SYSTEM - A system and method is disclosed for capturing images of one or more moving vehicles (i.e., a target vehicle) from another moving vehicle (i.e., subject vehicle). The disclosed system dynamically adjusts illumination power, exposure times, and/or other settings to optimize image capture that takes into account distance and speed. By optimizing for distances and moving vehicles, the disclosed system improves the probability of capturing a legible, usable photographic image. In one example, the disclosed system may be incorporated into an asymmetric license plate reading (ALPR) system. | 2020-11-05 |
20200349381 | Frame Level And Video Level Text Detection In Video - In some embodiments, a method detects a first set of frames in a video that include lines of text, the detecting performed at a frame level on each individual frame. A first representation is generated from the first set of frames and a second representation is generated from the first set of frames. The method filters the first representation based on a number of lines of text within a space in the space dimension to select a second set of frames and filters the second representation based on a number of frames within time intervals in the time dimension to select a third set of frames. Frames in both the second set of frames and the third set of frames are analyzed to determine whether the lines of text in both the second set of frames and the third set of frames are burned-in subtitles. | 2020-11-05 |
20200349382 | METHOD AND COMPUTING DEVICE FOR ADJUSTING REGION OF INTEREST - A method and a computing device for adjusting a region of interest (ROI) are provided. The method includes: receiving a image sequence including a current image and a previous image; generating a predefined searching area based on a previous ROI in the previous image; performing feature matching on multiple image features within the predefined searching area in the previous image and multiple image features within the predefined searching area in the current image; and adjusting a position of the previous ROI in the previous image based on the image features within the predefined searching area in the current image in response to that the image features within the predefined searching area in the current image satisfy a matching condition to obtain the current ROI in the current image. | 2020-11-05 |
20200349383 | OPTICAL SPRAY PATTERN IMAGING APPARATUS FOR GENERATING IMAGES INCLUDING DENSITY IMAGE FEATURES - A spray pattern imaging apparatus, and method of operation, is described herein. The method is carried out by the spray pattern imaging apparatus that includes a frame having a set of known aspects corresponding to a first dimension and a second dimension within a first plane. The spray pattern imaging apparatus also includes a light source generating a planar light pattern within a substantially same plane as the first plane of the frame. The set of known aspects facilitate both correcting an image distortion and a scaling of a spray pattern image generated by an image acquisition device during a spray application by a nozzle positioned in a physical relationship with the planar light pattern such that spray particles emitted from the spray nozzle pass through the planar light pattern while an initial image is acquired by the image acquisition device. | 2020-11-05 |
20200349384 | METHOD AND APPARATUS FOR PRESENTING MATERIAL, AND STORAGE MEDIUM - Disclosed are a method and apparatus for presenting material, and a storage medium. The method includes acquiring at least two key points from a position of a presentation part of an object in an image; determining a preselected target point based on positions of the at least two key points; determining a target point of the image based on the preselected target point and target points of N continuous frames before the image, and presenting the material based on the target point. | 2020-11-05 |
20200349385 | MULTIMEDIA RESOURCE MATCHING METHOD AND APPARATUS, STORAGE MEDIUM, AND ELECTRONIC APPARATUS - This application discloses a multimedia resource matching method performed at a computing device. The method includes: searching a first media resource set among a multimedia resource set, first target image frames of all media resources in the first media resource set meeting a target condition, and features of the first target image frames matching features in image frames of a to-be-matched multimedia resource according to a first matching condition; determining, among the first target image frames, second target image frames whose features match the features in the image frames of the to-be-matched multimedia resource according to a second matching condition; and obtaining matching information of the second target image frames and an identifier of a target media resource among the multimedia resource set, the matching information being used for indicating a total duration and a playback moment of the second target frame image in the target media resource. | 2020-11-05 |
20200349386 | Storing Information for Access Using a Captured Image - An electronic device comprising circuitry configured to associate first information and at least a first portion of a first image, and circuitry configured to use a second image that includes a portion corresponding to at least the first portion of the first image to access the associated first information. | 2020-11-05 |
20200349387 | MAPPING VISUAL TAGS TO SOUND TAGS USING TEXT SIMILARITY - Sound effects (SFX) are registered in a database for efficient search and retrieval. This may be accomplished by classifying SFX and using a machine learning engine to output a first of the classified SFX for a first computer simulation based on learned correlations between video attributes of the first computer simulation and the classified SFX. Subsequently, videos without sound may be processed for object, action, and caption recognition to generate video tags which are semantically matched with SFX tags to associate SFX with the video. | 2020-11-05 |
20200349388 | METHOD FOR EXTRACTING FEATURE STRING, DEVICE, NETWORK APPARATUS, AND STORAGE MEDIUM - Disclosed are a method for extracting a feature string, a device, a network apparatus, and a storage medium. The method comprises: determining, for each candidate feature string, a transition probability for each pair of adjacent characters in the candidate feature string according to a first-order Markov transition probability matrix; determining a transition entropy value of the candidate feature string according to the transition probability of each pair of adjacent characters and the logarithm of the transition probability; and labeling a candidate feature string having a transition entropy value greater than a pre-determined threshold as a first usable feature string, and using a valid first usable feature string as an extracted target feature string. In embodiments of the present invention, transition entropy values of candidate feature strings of a data packet are determined according to a first-order Markov transition probability matrix, a candidate feature string having a transition entropy value meeting a requirement is labeled as a first usable feature string, and a valid first usable feature string is used as an extracted target feature string. The method for extracting a feature string provided in the embodiments of the present invention does not require manual intervention and achieves fully automatic extraction of a feature string. | 2020-11-05 |
20200349389 | METHOD AND DEVICE FOR TRAINING IMAGE RECOGNITION MODEL AND RELATED DEVICE - The present disclosure relates to a method and a device for training an image recognition model and a related device. The method includes: extracting sub-image feature data from a detection frame sub-image of an input image; determining element feature data matching the sub-image feature data from an index element database; and outputting images related to the element feature data as training images for training the image recognition model. The index element database is built in advance based on a plurality of element feature data extracted from a plurality of candidate images. | 2020-11-05 |
20200349390 | ARTIFICIAL INTELLIGENCE BASED ANNOTATION FRAMEWORK WITH ACTIVE LEARNING FOR IMAGE ANALYTICS - Systems and techniques for providing an artificial intelligence based annotation framework with active learning for image analytics are presented. In one example, a system annotates training data associated with a set of images for a feature learning process. The system also incrementally updates an analytics artificial intelligence model for an engineering component based on the feature learning process. | 2020-11-05 |
20200349391 | METHOD FOR TRAINING IMAGE GENERATION NETWORK, ELECTRONIC DEVICE, AND STORAGE MEDIUM - A method for training an image generation network, an electronic device and a storage medium are provided. The method includes: obtaining a sample image, where the sample image includes a first sample image and a second sample image corresponding to the first sample image; processing the first sample image based on an image generation network to obtain a predicted target image; determining a difference loss between the predicted target image and the second sample image; and training the image generation network based on the difference loss to obtain a trained image generation network. | 2020-11-05 |
20200349392 | ON-THE-FLY DEEP LEARNING IN MACHINE LEARNING AT AUTONOMOUS MACHINES - A mechanism is described for facilitating the transfer of features learned by a context independent pre-trained deep neural network to a context dependent neural network. The mechanism includes extracting a feature learned by a first deep neural network (DNN) model via the framework, wherein the first DNN model is a pre-trained DNN model for computer vision to enable context-independent classification of an object within an input video frame and training, via the deep learning framework, a second DNN model for computer vision based on the extracted feature, the second DNN model an update of the first DNN model, wherein training the second DNN model includes training the second DNN model based on a dataset including context-dependent data. | 2020-11-05 |
20200349393 | Optimizing Supervised Generative Adversarial Networks via Latent Space Regularizations - A method of training a generator G of a Generative Adversarial Network (GAN) includes receiving, by an encoder E, a target data Y; receiving, by the encoder E, an output G(Z) of the generator G, where the generator G generates the output G(Z) in response to receiving a random sample Z that is a noisy sample, and where a discriminator D of the GAN is trained to distinguish which of the G(Z) and the target data Y is real data; training the encoder E to minimize a difference between a first latent space representation E(G(Z)) of the output G(Z) and a second latent space representation E(Y) of the target data Y, where the output G(Z) and the target data Y are input to the encoder E; and using the first latent space representation E(G(Z)) and the second latent space representation E(Y) to constrain the training of the generator G. | 2020-11-05 |
20200349394 | CLASSIFICATION AND LOCALIZATION BASED ON ANNOTATION INFORMATION - Systems and techniques for classification and localization based on annotation information are presented. In one example, a system trains a convolutional neural network based on training data and a plurality of images. The training data is associated with a plurality of patients from at least one imaging device. The plurality of images is associated with a plurality of masks from a plurality of objects. The convolutional neural network comprises a decoder consisting of at least one up-sampling layer and at least one convolutional layer. The system also generates a loss function based on the plurality of masks, where the loss function is iteratively back propagated to tune parameters of the convolutional neural network. The system also predicts a classification label for an input image based on the convolutional neural network. | 2020-11-05 |
20200349395 | CHARACTERIZING FAILURES OF A MACHINE LEARNING MODEL BASED ON INSTANCE FEATURES - The present disclosure relates to systems, methods, and computer readable media that evaluate performance of a machine learning system in connection with a test dataset. For example, systems disclosed herein may receive a test dataset and identify label information for the test dataset including feature information and ground truth data. The systems disclosed herein can compare the ground truth data and outputs generated by a machine learning system to evaluate performance of the machine learning system with respect to the test dataset. The systems disclosed herein may further generate feature clusters based on failed outputs and corresponding features and generate a number of performance views that illustrate performance of the machine learning system with respect to clustered groupings of the test dataset. | 2020-11-05 |
20200349396 | ELECTRONIC DEVICE AND MODEL UPDATING METHOD - An electronic device and a model updating method are provided. The method includes: inputting a plurality of files to a first model and outputting a predicted result of each of the plurality of files; receiving a corrected result for correcting the prediction result of at least one first file in the plurality of files, and generating a first label file corresponding to the at least one first file according to the corrected result and the first file; training a plurality of models according to the first label file to generate a plurality of a trained model; testing the plurality of trained models using at least one test set; and replacing the first model with a first trained model when the predicting accuracy of the first trained model of the plurality of trained models is higher than the predicting accuracy of the first model. | 2020-11-05 |
20200349397 | INSECT SINGULATION AND CLASSIFICATION - An insect sortation system can track movement of insects along a predefined pathway. The insect sortation system includes a puff-back system for moving insects toward an inlet of the pathway and a puff-forward system for moving insects toward an outlet of the pathway. An overhead imaging system captures images of the insects at one or more locations along the pathway. Once imaged, the insect may be classified into a category (e.g., sex category, species category, size category, etc.) using a variety of different classification approaches including, for example, an industrial vision classifier and/or a machine learning classifier. Once classified, the insects can be directed to various chambers for subsequent processing. | 2020-11-05 |
20200349398 | INDUCTION HEATING SYSTEMS - A method for performing mold remediation includes placing a ferromagnetic material in or adjacent to a surface upon which mold is located. The method also includes emitting, by an electromagnetic radiation source, radiation to heat the ferromagnetic material that is adjacent to the surface upon which the mold is located. The method also includes detecting, by a temperature sensor, a temperature of the surface. The method further includes comparing, by a processor in communication with the electromagnetic radiation source and the temperature sensor, the temperature of the surface to a desired temperature to perform mold remediation. | 2020-11-05 |
20200349399 | SYSTEM AND METHOD FOR AUTOMATIC ASSESSMENT OF CANCER - Cancer can be an aggressive disease. It is critical to determine the most effective patient-specific treatment quickly. Exemplary embodiments use a data-driven approach to extracting tumor information from data obtain from Whole Slide Image that is uploaded through an interface. Exemplary embodiments generate the following information about a tumor from a biopsy slide using neural networks: annotated areas of relevant tissues, molecular subtype, and expression status of an important gene and include three steps: the segmentation of tumor features; prediction of molecular subtype; and prediction of gene methylation status from a WSI. | 2020-11-05 |
20200349400 | Machine Learning Model Score Obfuscation Using Step Function, Position-Dependent Noise - An artefact is received. Features are extracted from this artefact which are, in turn, used to populate a vector. The vector is then input into a classification model to generate a score. The score is then modified using a step function so that the true score is not obfuscated. Thereafter, the modified score can be provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described. | 2020-11-05 |
20200349401 | Machine Learning Model Score Obfuscation Using Vector Modification Techniques - An artefact is received. Features from such artefact are extracted and then populated in a vector. Subsequently, one of a plurality of available dimension reduction techniques are selected. Using the selected dimension reduction technique, the features in the vector are reduced. The vector is then input into a classification model and the score can be provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described. | 2020-11-05 |
20200349402 | GENERATING REPORTS OF THREE DIMENSIONAL IMAGES - Various techniques are provided for generating reports of three dimensional (3D) images. The techniques include identifying a plurality of volume features in a 3D image using a first machine learning (ML) module trained with annotated 3D images, and identifying a plurality of semantic representations associated with the 3D image using a second ML module trained with the annotated 3D images and reports associated with the annotated 3D images. The techniques further include generating a report of the 3D image based on the volume features and the semantic representations using a third ML module trained with the reports and outputs generated by the first ML module and the second ML module using the annotated 3D images and the reports. | 2020-11-05 |
20200349403 | GRAPHIC ADAPTATION METHOD AND SYSTEM FOR CERAMIC SUPPORTS, SPECIFICALLY TILES - A graphics adaptation method for printable ceramic supports. Images are printed on sample ceramic supports starting from an original image file. A sample printed image is acquired. Sample points representative of the sample image are selected. Original points present in the original image file are also selected. A point-based matching is sought between the sample points and the original points, on the basis of which the original image file is modified and an adapted image file is determined, thus adapting the graphics of the original image file to the graphics of the sample image. A graphics adaptation system based on the method is also described. | 2020-11-05 |
20200349404 | PROBABILISTIC PIXEL BIASING IN LOW AREA COVERAGE - Methods, apparatuses, devices, and systems are disclosed herein for upscaling an input image to a higher resolution while simultaneously converting the image data from a multi-drop state to a binary state. These systems and methods use a probabilistic combination of randomized and biased positioning of inkjet firings in order to yield perceptibly lower graininess in low-coverage areas of output prints without introducing new artefacts. | 2020-11-05 |
20200349405 | IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD AND STORAGE MEDIUM - An image processing apparatus that generates image data to be output to an image forming apparatus printing an image, and includes: a generation unit configured to generate, based on an input image, first generation amount data indicating a generation amount of each of one or more kinds of ink dot for each pixel and second generation amount data indicating a generation amount of a blank dot for which the ink dot is not formed for each pixel; and a processing unit configured to determine a dot arrangement pattern indicating an arrangement of each of the one or more kinds of ink dot by performing quantization processing using the first generation amount data and the second generation amount data. | 2020-11-05 |
20200349406 | Face Image Processing Method and Device - A face image processing method is provided. The face processing method comprising: extracting a plurality of features from a primary two-dimensional face image to generate a first feature vector; decomposing a three-dimensional face image into a plurality of base face images and a plurality of weighting factors corresponding to the base face images; generating a first two-dimensional code according to the first feature vector; and generating a second two-dimensional code according to the weighting factors. | 2020-11-05 |
20200349407 | DUAL FREQUENCY HF-UHF IDENTIFICATION INTEGRATED CIRCUIT - A dual frequency HF-UHF RFID integrated circuit including a power supply. The power supply includes: an HF branch including an HF rectifier and a linear voltage regulator, wherein the HF rectifier is configured to be connected to a resonance circuit formed by a HF antenna-coil and a resonance capacitor and wherein the HF rectifier is connected to the linear voltage regulator; a UHF branch including a UHF rectifier and a shunt voltage regulator, wherein the UHF rectifier has a charge pump and is configured to be connected to a UHF antenna and wherein the UHF rectifier is connected to the shunt voltage regulator; and a supply line, wherein the linear voltage regulator and the shunt voltage regulator are both connected to the supply line of the power supply. | 2020-11-05 |
20200349408 | ENROLMENT CASE FOR SMART CARD - Disclosed is a semi-rigid enrolment case for a smart card, formed by folding and gluing an envelope-like cardboard blank of the dimensions of the card. The case includes an electrical circuit printed directly on the cardboard of an inner surface. The circuit includes contact studs connected to a power supply interface and arranged to connect electrical contacts of the card to the power supply interface when the card is inserted into the case. A biometric sensor of the card remains accessible to the user when it is out of the case for making the enrolment. Through-openings are made in the cardboard on either side of contact stud lines and allow forming independent flexible areas, providing better contact between the studs and the electrical contacts of the card. | 2020-11-05 |
20200349409 | CARD-TYPE ELECTRONIC DEVICE CAPABLE OF SUPPRESSING RISE IN TEMPERATURE, SLOT, AND ELECTRONIC APPARATUS - A card-type electronic device capable of suppressing a rise in the temperature of signal lines for high-speed communication requiring impedance control while ensuring sufficient thermal connection and electrical connection. A connector is fixed to a substrate on which electronic components that generate heat are mounted, and includes electrical contacts electrically connected to an external apparatus and a thermal contact thermally connected to the external apparatus. A cutout is formed in the substrate between a portion to which the thermal contact is fixed and a portion to which the electrical contacts are fixed. | 2020-11-05 |
20200349410 | Post-Cure Read Range Enhancement Of RFID Tire Tags - Methods for increasing the read range of an electronic communication module within a tire and methods for improving the read range of an electronic communication module within a tire are provided herein. As discussed further herein, the read range can be increased by applying strain to the tire without abrading its tread, resulting in an increase in read range of 20% or more. Similarly, the read range can be improved by applying strain to the tire without circumferentially contacting the outer surface of its tread, resulting in an increase in the same-distance-signal-strength of 5% or more. Also provided are tires made according to the disclosed methods. | 2020-11-05 |
20200349411 | SYSTEM AND METHOD FOR INVERTIBLE WAVELET LAYER FOR NEURAL NETWORKS - An electronic device, method, and computer readable medium for an invertible wavelet layer for neural networks are provided. The electronic device includes a memory and at least one processor coupled to the memory. The at least one processor is configured to receive an input to a neural network, apply a wavelet transform to the input at a wavelet layer of the neural network, and generate a plurality of subbands of the input as a result of the wavelet transform. | 2020-11-05 |
20200349412 | PROSPECTIVE MEDIA CONTENT GENERATION USING NEURAL NETWORK MODELING - A system for prospectively identifying media characteristics for inclusion in media content is disclosed. A neural network database including media characteristic information and feature information may associate relationships among the media characteristic information and feature information. Personal characteristic information associated with target media consumers may be used to select a subset of the neural network database. A first set of nodes, representing selected feature information, may be activated. The node interactions may be calculated to detect the activation of a second set of nodes, the second set of nodes representing media characteristic information. Generally, a node is activated when an activation value of the node exceeds a threshold value. Media characteristic information may be identified for inclusion in media content based on the second set of nodes. | 2020-11-05 |
20200349413 | SCALABLE MODEL SERVING - A neural network models fragmenting method, system, and computer program product include recursively factoring out common prefixes of models, constructing a hierarchy of decomposed model fragments based on the factoring, and grouping the constructed hierarchy for deployment. | 2020-11-05 |
20200349414 | SYSTEMS AND METHODS FOR NEURONAL NETWORKS FOR ASSOCIATIVE GESTALT LEARNING - Systems and methods for neuronal networks for associative learning are described. For example, a method may include obtaining target content, obtaining conditioned feature extraction models, generating multiple extracted features by applying the conditioned feature extraction models to the target content, obtaining a conditioned integration model, generating a representation of the target content by applying the conditioned integration model to the multiple extracted features, and displaying the representation. | 2020-11-05 |
20200349415 | METHOD FOR CAPTURING AND STORING CONTACT INFORMATION FROM A PHYSICAL MEDIUM USING MACHINE LEARNING - Described herein are systems and methods for facilitating the information entry and task updates to a task database in a cloud server. The task database is in synchronization with a customer relationship management (CRM) system. The systems and methods described herein enable users to update the task database and enter information into the task database in a timely manner such that the task database can stay updated. The updated database can be used to construct a suggested task set at the beginning of a period of time to meet a preset target sales value for the end of the period of time. In one embodiment, a system includes a mobile application to capture contact information from a physical medium as an image, and to send the image to a cloud server, where a trained neural network model is to extract contact details and send the contact details back to the mobile application for editing and confirmation by a user. The confirmed contact details can then be persisted into the task database as a new task, part of a new task, or part of an existing task. | 2020-11-05 |
20200349416 | DETERMINING COMPUTER-EXECUTED ENSEMBLE MODEL - Implementations of the present specification provide a method for determining a computer-executed ensemble model. The method includes: obtaining a current ensemble model and a plurality of untrained candidate submodels; integrating each of the plurality of candidate submodels into the current ensemble model to obtain a plurality of first candidate ensemble models; training at least the plurality of first candidate ensemble models to obtain a plurality of second candidate ensemble models after this training; performing performance evaluation on each of the plurality of second candidate ensemble models to obtain corresponding performance evaluation results; determining, based on the performance evaluation results, an optimal candidate ensemble model with optimal performance from the plurality of second candidate ensemble models; and updating the current ensemble model with the optimal candidate ensemble model if the performance of the optimal candidate ensemble model satisfies a predetermined condition. | 2020-11-05 |
20200349417 | SYSTEMS AND METHODS TO DEMONSTRATE CONFIDENCE AND CERTAINTY IN FEEDFORWARD AI METHODS - A computer-implemented method includes obtaining a first neural network trained to recognize one or more patterns; converting said first neural network to a mathematically equivalent second network; and then using said second network to determine one or more factors that influence pattern recognition by said first neural network. | 2020-11-05 |
20200349418 | GATED LINEAR NETWORKS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a neural network system comprising one or more gated linear networks. A system includes: one or more gated linear networks, wherein each gated linear network corresponds to a respective data value in an output data sample and is configured to generate a network probability output that defines a probability distribution over possible values for the corresponding data value, wherein each gated linear network comprises a plurality of layers, wherein the plurality of layers comprises a plurality of gated linear layers, wherein each gated linear layer has one or more nodes, and wherein each node is configured to: receive a plurality of inputs, receive side information for the node; combine the plurality of inputs according to a set of weights defined by the side information, and generate and output a node probability output for the corresponding data value. | 2020-11-05 |
20200349419 | NEURAL NETWORK ARITHMETIC PROCESSING DEVICE AND NEURAL NETWORK ARITHMETIC PROCESSING METHOD - A neural network arithmetic processing device is capable of implementing a further increase in speed and efficiency of multiply-accumulate arithmetic operation, suppressing an increase in circuit scale, and performing multiply-accumulate arithmetic operation with simple design. A neural network arithmetic processing device includes a first multiply-accumulate arithmetic unit, a register connected to the first multiply-accumulate arithmetic unit, and a second multiply-accumulate arithmetic unit connected to the register. The first multiply-accumulate arithmetic unit has a first memory, a second memory, a first multiplier, a first adder, and a first output unit. The second multiply-accumulate arithmetic unit has an input unit, a third memory, second multipliers, second adders, and second output units. | 2020-11-05 |
20200349420 | MIXED-PRECISION NPU TILE WITH DEPTH-WISE CONVOLUTION - A processor to perform inference on deep learning neural network models. In some embodiments, the process includes: a first tile, a second tile, a memory, and a bus, the bus being connected to: the memory, the first tile, and the second tile, the first tile including: a first weight register, a second weight register, an activations cache, a shuffler, an activations buffer, a first multiplier, and a second multiplier, the activations buffer being configured to include: a first queue connected to the first multiplier, and a second queue connected to the second multiplier, the activations cache including a plurality of independent lanes, each of the independent lanes being randomly accessible, the first tile being configured: to receive a tensor including a plurality of two-dimensional arrays, each representing one color component of the image; and to perform a convolution of a kernel with one of the two-dimensional arrays. | 2020-11-05 |
20200349421 | CONFIGURABLE INPUT BLOCKS AND OUTPUT BLOCKS AND PHYSICAL LAYOUT FOR ANALOG NEURAL MEMORY IN DEEP LEARNING ARTIFICIAL NEURAL NETWORK - Configurable input blocks and output blocks and physical layouts are disclosed for analog neural memory systems that utilize non-volatile memory cells. An input block can be configured to support different numbers of arrays arranged in a horizontal direction, and an output block can be configured to support different numbers of arrays arranged in a vertical direction. Adjustable components are disclosed for use in the configurable input blocks and output blocks. | 2020-11-05 |
20200349422 | OUTPUT ARRAY NEURON CONVERSION AND CALIBRATION FOR ANALOG NEURAL MEMORY IN DEEP LEARNING ARTIFICIAL NEURAL NETWORK - Configurable input blocks and output blocks and physical layouts are disclosed for analog neural memory systems that utilize non-volatile memory cells. An input block can be configured to support different numbers of arrays arranged in a horizontal direction, and an output block can be configured to support different numbers of arrays arranged in a vertical direction. Adjustable components are disclosed for use in the configurable input blocks and output blocks. Systems and methods are utilized for compensating for leakage and offset in the input blocks and output blocks the in analog neural memory systems. | 2020-11-05 |
20200349423 | SEMICONDUCTOR DEVICE AND SYSTEM USING THE SAME - To provide a semiconductor device which can execute the product-sum operation. The semiconductor device includes a first memory cell, a second memory cell, and an offset circuit. First analog data is stored in the first memory cell, and reference analog data is stored in the second memory cell. The first memory cell and the second memory cell supply a first current and a second current, respectively, when a reference potential is applied as a selection signal. The offset circuit has a function of supplying a third current corresponding to a differential current between the first current and the second current. In the semiconductor device, the first memory and the second memory supply a fourth current and a fifth current, respectively, when a potential corresponding to second analog data is applied as a selection signal. By subtracting the third current from a differential current between the fourth current and the fifth current, a current that depends on the sum of products of the first analog data and the second analog data is obtained. | 2020-11-05 |
20200349424 | MEMORY LAYOUTS AND CONVERSION TO IMPROVE NEURAL NETWORK INFERENCE PERFORMANCE - Memory layout and conversion are disclosed to improve neural network (NN) inference performance. For one example, a NN selects a memory layout for a neural network (NN) among a plurality of different memory layouts based on thresholds derived from performance simulations of the NN. The NN stores multi-dimensional NN kernel computation data using the selected memory layout during NN inference. The memory layouts to be selected can be a channel, height, width, and batches (CHWN) layout, a batches, height, width and channel (NHWC) layout, and a batches, channel, height and width (NCHW) layout. If the multi-dimensional NN kernel computation data is not in the selected memory layout, the NN transforms the multi-dimensional NN kernel computation data for the selected memory layout. | 2020-11-05 |
20200349425 | TRAINING TIME REDUCTION IN AUTOMATIC DATA AUGMENTATION - A method may include obtaining a deep neural network model and obtaining a first training data point and a second training data point for the deep neural network model during a first training epoch. The method may include determining a first robustness value of the first training data point and a second robustness value of the second training data point. The method may further include omitting augmenting the first training data point in response to the first robustness value satisfying a robustness threshold and augmenting the second training data point in response to the second robustness value failing to satisfy the robustness threshold. The method may also include training the deep neural network model on the first training data point and the augmented second training data point during the first training epoch. | 2020-11-05 |
20200349426 | CONVOLUTION STREAMING ENGINE FOR DEEP NEURAL NETWORKS - A method, an electronic device, and computer readable medium are provided. The method includes receiving an input into a neural network that includes a kernel. The method also includes generating, during a convolution operation of the neural network, multiple panel matrices based on different portions of the input. The method additionally includes successively combining each of the multiple panel matrices with the kernel to generate an output. Generating the multiple panel matrices can include mapping elements within a moving window of the input onto columns of an indexing matrix, where a size of the window corresponds to the size of the kernel. | 2020-11-05 |
20200349427 | ADAPTABLE ONLINE BREAKPOINT DETECTION OVER I/O TRACE TIME SERIES VIA DEEP NEURAL NETWORK AUTOENCODERS RE-PARAMETERIZATION - One example method includes accessing I/O traces, generating parameters based on the I/O traces, and defining an autoencoder deep neural network, training the autoencoder deep neural network using the parameters, collecting and storing new I/O traces, computing an encoded features difference series using the new I/O traces, detecting breakpoints in the encoded features difference series, evaluating a utility of the breakpoints, and performing an action based on the breakpoint utility evaluation. | 2020-11-05 |
20200349428 | MEMORY DEVICE AND OPERATION METHOD THEREOF - Provided is an operation method for a memory device, the memory device being used for implementing an Artificial Neural Network (ANN). The operation method includes: reading from the memory device a weight matrix of a current layer of a plurality of layers of the ANN to extract a plurality of neuro values; determining whether to perform calibration; when it is determined to perform calibration, recalculating and updating a mean value and a variance value of the neuro values; and performing batch normalization based on the mean value and the variance value of the neuro values. | 2020-11-05 |
20200349429 | SYSTEMS AND METHODS FOR RECOGINIZING USER INFORMATION - A conferencing system is configured, for an interval of time, to receive time-dependent input data from a first user, the time-dependent input data obtained via a capturing device. The conferencing system is configured to receive profile data for the first user, analyze the time-dependent input data and the profile data for the first user using a computer-based model to obtain at least one classifier score for a classifier of a reaction of the first user, and transmit the at least one classifier score for the classifier to a second user. | 2020-11-05 |
20200349430 | SYSTEM AND METHOD FOR PREDICTING DOMAIN REPUTATION - A computer system comprising a processor and a memory storing instructions that, when executed by the processor, cause the computer system to perform a set of operations. The set of operations comprises collecting domain attribute data comprising one or more domain attribute features for a domain, collecting sampled domain profile data comprising one or more domain profile features for the domain and generating, using the domain attribute data and the sampled domain profile data, a domain reputation assignment utilizing a neural network. | 2020-11-05 |
20200349431 | SYSTEM REINFORCEMENT LEARNING METHOD AND APPARATUS, AND COMPUTER STORAGE MEDIUM - A system reinforcement learning method includes: processing an input image based on a first network of a system to obtain a first result; inputting the first result to a second network of the system to obtain a second result; and obtaining a reinforcement operation based on the second result by means of a reinforcement network, and adjusting the first result based on the reinforcement operation to obtain a target result. According to the embodiments of the present disclosure, information is fed back from downstream to upstream by means of the reinforcement network, and an output result of the system is optimized. | 2020-11-05 |
20200349432 | OPTIMIZED NEURAL NETWORK INPUT STRIDE METHOD AND APPARATUS - A convolutional layer in a convolutional neural network uses a predetermined horizontal input stride and a predetermined vertical input stride that are greater than 1 while the hardware forming the convolutional layer operates using an input stride of 1. Each original weight kernel of a plurality of sets of original weight kernels is subdivided based on the predetermined horizontal and vertical input strides to form a set of a plurality of sub-kernels for each set of original weight kernels. Each of a plurality of IFMs is subdivided based on the predetermined horizontal and vertical input strides to form a plurality of sub-maps. Each sub-map is convolved by the corresponding sub-kernel for a set of original weight kernels using an input stride of 1. A convolved result of each sub-map and the corresponding sub-kernel is summed to form an output feature map. | 2020-11-05 |
20200349433 | STREAMING-BASED ARTIFICIAL INTELLIGENCE CONVOLUTION PROCESSING METHOD AND APPARATUS, READABLE STORAGE MEDIUM AND TERMINAL - Provided is a streaming-based artificial intelligence convolution processing method, applied to a processing module. The method includes: adding invalid data to a starting point of a first to-be-processed data matrix stored in a first streaming lake to form a second to-be-processed data matrix, where a number of columns of the second to-be-processed data matrix is an integral multiple of a degree of parallelism of data transmission; using a data transmission module to take out the second to-be-processed data matrix from the first streaming lake in a preset manner for a convolution operation. Also provided are a streaming-based artificial intelligence convolution processing apparatus, a readable storage medium and a terminal. | 2020-11-05 |
20200349434 | DETERMINING CONFIDENT DATA SAMPLES FOR MACHINE LEARNING MODELS ON UNSEEN DATA - Techniques are provided for determining confident data samples for machine learning (ML) models on unseen data. In one embodiment, a method is provided that comprises extracting, by a system comprising a processor, a feature vector for a data sample based on projection of the data sample onto a standard feature space. The method further comprises processing, by the system, the feature vector using an outlier detection model to determine whether the data sample is within a scope of a training dataset used to train a machine learning model, wherein the outlier detection model was trained using features extracted from the training dataset based on projection of data samples included in the training dataset onto the standard feature space. | 2020-11-05 |
20200349435 | Secure Training of Multi-Party Deep Neural Network - A deep neural network may be trained on the data of one or more entities, also know as Alices. An outside computing entity, also known as a Bob, may assist in these computations, without receiving access to Alices' data. Data privacy may be preserved by employing a “split” neural network. The network may comprise an Alice part and a Bob part. The Alice part may comprise at least three neural layers, and the Bob part may comprise at least two neural layers. When training on data of an Alice, that Alice may input her data into the Alice part, perform forward propagation though the Alice part, and then pass output activations for the final layer of the Alice part to Bob. Bob may then forward propagate through the Bob part. Similarly, backpropagation may proceed backwards through the Bob part, and then through the Alice part of the network. | 2020-11-05 |
20200349436 | IMAGE SEARCHING - As provided herein, a domain model, corresponding to a domain of an image, may be merged with a pre-trained fundamental model to generate a trained fundamental model. The trained fundamental model may comprise a feature description of the image converted into a binary code. Responsive to a user submitting a search query, a coarse image search may be performed, using a search query binary code derived from the search query, to identify a candidate group, comprising one or more images, having binary codes corresponding to the search query binary code. A fine image search may be performed on the candidate group utilizing a search query feature description derived from the search query. The fine image search may be used to rank images within the candidate group based upon a similarity between the search query feature description and feature descriptions of the one or more images within the candidate group. | 2020-11-05 |
20200349437 | NEURAL EMBEDDINGS OF TRANSACTION DATA - Systems, methods, and computer program products to provide neural embeddings of transaction data. A network graph of transaction data based on a plurality of transactions may be received. The network graph of transaction data may define relationships between the transactions, each transaction associated with at least a merchant and an account. A neural network may be trained based on training data comprising a plurality of positive entity pairs and a plurality of negative entity pairs. An embedding function may then encode transaction data for a first new transaction. An embeddings layer of the neural network may determine a vector for the first new transaction based on the encoded transaction data for the first new transaction. A similarity between the vectors for the transactions may be determined. The first new transaction may be determined to be related to the second transaction based on the similarity. | 2020-11-05 |
20200349438 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM - There is provided an information processing apparatus as a mechanism capable of more appropriately specifying reasons of prediction by a prediction model, the information processing apparatus including a control unit configured to extract a characteristic amount set from characteristic amounts included in a plurality of pieces of input data input to a prediction model configured by a non-linear model, in which an absolute value of a degree of contribution of the extracted characteristic amount set to a prediction result by the prediction model is equal to or greater than a first threshold, and an absolute value of a degree of contribution of a characteristic amount set obtained by excluding arbitrary one of the characteristic amounts from the extracted characteristic amount set to a prediction result by the prediction model is equal to or less than a second threshold. | 2020-11-05 |
20200349439 | SYSTEM AND METHOD FOR CONVOLUTIONAL LAYER STRUCTURE FOR NEURAL NETWORKS - An electronic device, method, and computer readable medium for 3D association of detected objects are provided. The electronic device includes a memory and at least one processor coupled to the memory. The at least one processor configured to convolve an input to a neural network with a basis kernel to generate a convolution result, scale the convolution result by a scalar to create a scaled convolution result, and combine the scaled convolution result with one or more of a plurality of scaled convolution results to generate an output feature map. | 2020-11-05 |
20200349440 | DNN Training with Asymmetric RPU Devices - In one aspect, a method of training a DNN includes: providing a weight matrix (W) as a linear combination of matrices/arrays A and C; in a forward cycle, transmitting an input vector x through arrays A and C and reading output vector y; in a backward cycle, transmitting an error signal S through arrays A and C and reading output vector z; updating array A by transmitting input vector x and error signal S through array A; in a forward cycle, transmitting an input vector e | 2020-11-05 |
20200349441 | INTERPRETABLE NEURAL NETWORK - A method of operating a neural network, comprising: at each input node of an input layer, weighting a respective input element received by that node by applying a first class of probability distribution, thereby generating a respective set of output parameters describing an output probability distribution; and from each input node, outputting the respective set of output parameters to one or more nodes in a next, hidden layer of the network, thereby propagating the respective set of output parameters through the hidden layers to an output layer; the propagating comprising, at one or more nodes of at least one hidden layer, combining the sets of input parameters and weighting the combination by applying a second class of probability distribution, thereby generating a respective set of output parameters describing an output probability distribution, wherein the first class of probability distribution is more sparsity inducing than the second class of probability distribution. | 2020-11-05 |
20200349442 | AUTO FEED FORWARD/BACKWARD AUGMENTED REALITY LEARNING SYSTEM - An auto feed forward/backward augmented reality learning system includes a processing device that defines an interactive object image and a controllable object image and has a training database for storing and defining a hierarchical value of the interactive object image. The interactive object image shows different motion statuses by the hierarchical value. The processing device selects the hierarchical value according to a user's image and amount of exercise and defines a feedback value according to a result of the interaction between the user and the interactive object image. The processing device maintains or corrects the hierarchical value by the feedback value, and the learning system can change the way and status of showing the interactive object image according to the user's gender, age, height, and physical fitness without requiring expensive image recognition and computation facilities. The learning system may custom-made to fit different users' learning mode or physical training intensity. | 2020-11-05 |
20200349443 | Methods and apparatus for reducing leakage in distributed deep learning - A distributed deep learning network may prevent an attacker from reconstructing raw data from activation outputs of an intermediate layer of the network. To achieve this, the loss function of the network may tend to reduce distance correlation between raw data and the activation outputs. For instance, the loss function may be the sum of two terms, where the first term is weighted distance correlation between raw data and activation outputs of a split layer of the network, and the second term is weighted categorical cross entropy of actual labels and label predictions. Distance correlation with the entire raw data may be minimized. Alternatively, distance correlation with only with certain features of the raw data may be minimized, in order to ensure attribute-level privacy. In some cases, a client computer calculates decorrelated representations of raw data before sharing information about the data with external computers. | 2020-11-05 |
20200349444 | DATA PROCESSING SYSTEM AND DATA PROCESSING METHOD - A data processing system includes a learning unit that optimizes optimization target parameters of a neural network on the basis of a comparison between output data that is output by execution of a process according to a neural network on learning data and ideal output data for the learning data. An activation function f(x) of the neural network is defined, when a first parameter is C and a second parameter being a non-negative value is W, as a function in which an output value for an input value is a value continuous within a range of C±W, the output value for the input value is uniquely determined, and a graph of the function is point-symmetric with respect to a point corresponding to f(x)=C. The learning unit optimizes the optimization target parameters that include the first parameter and the second parameter. | 2020-11-05 |
20200349445 | DATA PROCESSING SYSTEM AND DATA PROCESSING METHOD - A data processing system includes a learning unit that optimizes an optimization target parameter of a neural network on the basis of a comparison between output data that is output by execution of a process according to a neural network on learning data and ideal output data for the learning data. The learning unit optimizes a slope ratio parameter indicating a ratio of a slope when an input value is in a positive range and a slope when the input value is in a negative range in an activation function of the neural network, as one of optimization parameters. | 2020-11-05 |
20200349446 | TRAINING A NODAL NETWORK SO THAT A FIRST NODE HAS A HIGH MAGNITUDE CORRELATION WITH THE PARTIAL DERIVATIVE OF THE OBJECTIVE WITH RESPECT TO A SECOND NODE - A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network. | 2020-11-05 |
20200349447 | Optimizing Unsupervised Generative Adversarial Networks via Latent Space Regularizations - Training a generator G of a GAN includes generating, by G and in response to receiving a first input Z, a first output G(Z); generating, by an encoder E of the GAN and in response to receiving the first output G(Z) as input, a second output E(G(Z)); generating, by G and in response to receiving the second output E(G(Z)) as input, a third output G(E(G(Z))); generating, by E and in response to receiving the third output G(E(G(Z))) as input, a fourth output E(G(E(G(Z)))); training E to minimize a difference between the second output E(G(Z)) and the fourth output E(G(E(G(Z)))); and using the second output E(G(Z)) and fourth output E(G(E(G(Z)))) to constrain a training of the generator G. G(Z) is an ambient space representation Z. E(G(Z)) is a latent space representation of G(Z). G(E(G(Z))) is an ambient space representation of E(G(Z)). E(G(E(G(Z)))) is a latent space representation of G(E(G(Z))). | 2020-11-05 |
20200349448 | SYSTEMS, METHODS, AND DEVICES FOR BIOPHYSICAL MODELING AND RESPONSE PREDICTION - Various systems and methods are disclosed. One or more of the methods disclosed uses machine learning algorithms to predict biophysical responses from biophysical data, such as heart rate monitor data, food logs, or glucose measurements. Biophysical responses may include behavioral responses. Additional systems and methods extract nutritional information from food items by parsing strings containing names of food items. | 2020-11-05 |
20200349449 | 3-D CONVOLUTIONAL AUTOENCODER FOR LOW-DOSE CT VIA TRANSFER LEARNING FROM A 2-D TRAINED NETWORK - A 3-D convolutional autoencoder for low-dose CT via transfer learning from a 2-D trained network is described, A machine learning method for low dose computed tomography (LDCT) image correction is provided. The method includes training, by a training circuitry, a neural network (NN) based, at least in part, on two-dimensional (2-D) training data. The 2-D training data includes a plurality of 2-D training image pairs. Each 2-D image pair includes one training input image and one corresponding target output image. The training includes adjusting at least one of a plurality of 2-D weights based, at least in part, on an objective function. The method further includes refining, by the training circuitry, the NN based, at least in part, on three-dimensional (3-D) training data. The 3-D training data includes a plurality of 3-D training image pairs. Each 3-D training image pair includes a plurality of adjacent 2-D training input images and at least one corresponding target output image. The refining includes adjusting at least one of a plurality of 3-D weights based, at least in part, on the plurality of 2-D weights and based, at least in part, on the objective function. The plurality of 2-D weights includes the at least one adjusted 2-D weight. | 2020-11-05 |
20200349450 | PROJECTION NEURAL NETWORKS - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a projection neural network. In one aspect, a projection neural network is configured to receive a projection network input and to generate a projection network output from the projection network input. The projection neural network includes a sequence of one or more projection layers. Each projection layer has multiple projection layer parameters, and is configured to receive a layer input, apply multiple projection layer functions to the layer input, and generate a layer output by applying the projection layer parameters for the projection layer to the projection function outputs. | 2020-11-05 |
20200349451 | Physical Property Prediction Method and Physical Property Prediction System - A physical property prediction method that allows anyone to predict a physical property of an organic compound easily and accurately is provided. A physical property prediction system that allows anyone to predict a physical property of an organic compound easily and accurately is provided. Provided are a physical property prediction method including the step of learning a correlation between a molecular structure and a physical property of an organic compound and the step of predicting the target physical property value from the molecular structure of an object substance, and a physical property prediction system. A plurality of kinds of fingerprinting methods are used at the same time as notation methods of the molecular structure of the organic compound. | 2020-11-05 |
20200349452 | Big Data Based Predictive Graph Generation System - A big data analysis system may include a big data repository communicatively coupled to a data accumulation server and a predictive graph processing system. The data accumulation server may be configured to receive information from a plurality of data sources, the information corresponding to user interaction with one or more computing devices associated with an organization via a networked computing system, store the information received from the plurality of sources in the big data repository; and monitor the plurality of data sources to update the data stored in the big data repository. The predictive graph processing system is configured to receive information stored in the big data repository, transform the information received from the big data repository into a predictive graph data set based on a predictive model, and store the predictive graph data set to a visualization data repository. | 2020-11-05 |
20200349453 | METHOD AND SYSTEM FOR SOLVING A DYNAMIC PROGRAMMING PROBLEM - A method and a system are disclosed for solving a dynamic programming problem using a quantum computer. The method comprises receiving an indication of a dynamic programming problem, the dynamic programming problem comprising a plurality of transition kernels, receiving data representative of the dynamic programming problem, generating at least one oracle for the transition kernels of the dynamic programming problem, until a stopping criterion is met determining at least one linear programming problem for the dynamic programming problem, solving the at least one linear programming problem using a quantum computer comprising the generated at least one oracle to determine at least one solution, and providing the determined at least one solution; and providing a solution to the dynamic programming problem. | 2020-11-05 |
20200349454 | LOGICAL CALCULATION DEVICE, LOGICAL CALCULATION METHOD, AND PROGRAM - A logical calculation device includes: an inclusion extraction unit that extracts a set of first and second predicate logical formulas from a plurality of predicate logical formulas, each of the plurality of predicate logical formulas including a plurality of predicate arguments that include one predicate and one or more variables, a set of a closed formula in which each variable in the first predicate logical formula is substituted with a value including a set of a closed formula in which each variable in the second predicate logical formula is substituted with a value. | 2020-11-05 |
20200349455 | EXPLANATION-DRIVEN REASONING ENGINE - A device may receive a request to identify items that satisfy parameters of the request. The device may identify a plurality of items that satisfy the parameters. The device may generate a plurality of explanation sets. An explanation set of the plurality of explanation sets may relate to an item of the plurality of items. The explanation set may include at least one of: a positive explanation indicating that the item is positively associated with a first characteristic that relates to a first preference of a user, or a negative explanation indicating that the item is negatively associated with a second characteristic that relates to a second preference of the user. The device may select an item from the plurality of items based on the plurality of explanation sets. The device may provide information that includes an explanation set of the item selected. | 2020-11-05 |