26th week of 2021 patent applcation highlights part 53 |
Patent application number | Title | Published |
20210201033 | I/O SIGNAL INFORMATION DISPLAY SYSTEM - To provide an I/O signal information system in which a monitoring target portion and I/O signal information are automatically associated with each other and displayed on a display screen when monitoring a facility including a robot. An object identification unit identifies an object based on a correlation between a change of an actual photographed image displayed on a display device by actual photographed data supplied from an imaging device and a change of I/O signal information, and a display control unit causes the display device to display an augmented reality image in a display form in which an image of the I/O signal information has a specific relationship with an image of the object identified. | 2021-07-01 |
20210201034 | STATE QUANTITY ESTIMATION DEVICE, CONTROL DEVICE, AND STATE QUANTITY ESTIMATION METHOD - Realized is a technique for estimating a state quantity of a vehicle, which technique is applicable to estimation of a vehicle weight and allows an increase in accuracy and speed of the estimation. A state quantity estimating device includes a data storing section ( | 2021-07-01 |
20210201035 | Intelligent Agents for Managing Data Associated with Three-Dimensional Objects - The techniques disclosed herein improve the efficiency of a system by providing intelligent agents for managing data associated with objects that are displayed within mixed-reality and virtual-reality collaboration environments. Individual agents are configured to collect, analyze, and store data associated with individual objects in a shared view. The agents can identify real-world objects and virtual objects discussed in a meeting, collect information about each object and store the collected information in an associated database for access across multiple collaboration environments or communication sessions. The data can be shared between different communication sessions without requiring users to manually store and present a collection of content for each object. The intelligent agents and their associated databases can also persist through different communication sessions to enhance user engagement and improve productivity. | 2021-07-01 |
20210201036 | AUGMENTED REALITY SYSTEM USING STRUCTURED LIGHT - An augmented reality system having a light source and a camera. The light source projects a pattern of light onto a scene, the pattern being periodic. The camera captures an image of the scene including the projected pattern. A projector pixel of the projected pattern corresponding to an image pixel of the captured image is determined. A disparity of each correspondence is determined, the disparity being an amount that corresponding pixels are displaced between the projected pattern and the captured image. A three-dimensional computer model of the scene is generated based on the disparity. A virtual object in the scene is rendered based on the three-dimensional computer model. | 2021-07-01 |
20210201037 | VISUAL INSPECTION SUPPORT USING EXTENDED REALITY - A device having extended reality capabilities may capture a video feed including one or more video frames depicting an object that is visible in a field of view of the device. The device may provide the one or more video frames to a machine learning model that identifies the object and one or more parts of the object that are depicted in the one or more video frames. The device may obtain positional tracking information that represents a position and an orientation associated with the object relative to a coordinate space that corresponds to the field of view of the device. The device may obtain a workflow including a sequence of content items for visually inspecting the object using the extended reality capabilities of the device. The device may render digital content associated with the workflow using the extended reality capabilities of the device. | 2021-07-01 |
20210201038 | METHOD AND APPARATUS FOR VIDEO PROCESSING - Embodiments of the disclosure provides methods and apparatuses for video processing. In one embodiment, the video processing method comprises: obtaining at least one video from a video repository as a video to be processed; performing semantic recognition on the video in one or more semantic recognition dimensions to obtain one or more video label data items corresponding to the video in the one or more semantic recognition dimensions; generating at least one candidate label combination based on at least one of the one or more video label data items; determining, based on a target label combination selected by a user from the at least one candidate label combination, one or more video clips in the video corresponding to at least one video label in the target label combination; and generating at least one target video clip corresponding to the target label combination based on at least one of the one or more video clips. | 2021-07-01 |
20210201039 | Computer Vision Systems and Methods for Automatically Detecting, Classifying, and Pricing Objects Captured in Images or Videos - Systems and methods for automatically detecting, classifying, and processing objects captured in an images or videos are provided. In one embodiment, the system receives an image from an image source and detects one or more objects in the image. The system performs a high-level classification of the one or more objects in the image. The system performs a specific classification of the one or more objects, determines a price of the one or more objects, and generates a pricing report comprising a price of the one or more objects. In another embodiment, the system captures at least one image or video frame and classifies an object present in the image or video frame using a neural network. The system adds the classified object and an assigned object code to an inventory and processes the inventory to assign the classified object a price. | 2021-07-01 |
20210201040 | METHODS AND SYSTEMS FOR VIDEO PROCESSING - A method for processing an online video stream may include determining a transmission performance of a network for a queue of video frames, wherein each video frame in the queue may be associated with a priority level. The method may also include determining a maximum discarding level based on the transmission performance of the network. The method may further include removing a target video frame of which the associated priority level is lower than or equal to the maximum discarding level from the queue. | 2021-07-01 |
20210201041 | LOGO EXTRACTION DEVICE, AND BRIGHTNESS ADJUSTING METHOD AND DEVICE FOR LOGO - The present application discloses a logo extraction device, and a brightness adjusting method and device for a logo. The logo extraction device includes an acquiring module, a gray-scale converting module, a weight processing module, and an extraction module. In the present application, by increasing a number of key frames in a process of logo extraction and using video frame weighting, the logo is extracted and thereby accuracy of logo extraction is improved. | 2021-07-01 |
20210201042 | METHOD AND APPARATUS FOR DETECTING ABNORMAL OBJECTS IN VIDEO - Disclosed are a method and an apparatus for detecting abnormal objects in a video. The method for detecting abnormal objects in a video reconstructs a restored batch by applying each input batch to which an inpainting pattern is applied to a trained auto-encoder model, and fuses a time domain reconstruction error using time domain restored frames output by extracting and restoring a time domain feature point by applying a spatial domain reconstruction error and a plurality of successive frames using a restored frame output by combining the reconstructed restoring batch to a trained LSTM auto-encoder model to estimate an area where an abnormal object is positioned. | 2021-07-01 |
20210201043 | VIDEO SAMPLING METHOD AND APPARATUS USING THE SAME - A video sampling method, including sampling a video based on a sampling window to obtain a current sequence of sampled images; acquiring action parameters corresponding to the current sequence of sampled images; adjusting the sampling window according to the action parameters; and sampling the video based on the adjusted sampling window. | 2021-07-01 |
20210201044 | AUTOMATIC DIGITAL CONTENT CAPTIONING USING SPATIAL RELATIONSHIPS METHOD AND APPARATUS - Disclosed are systems and methods for improving interactions with and between computers in content hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods provide systems and methods for automatically creating a caption comprising a sequence of words in connection with digital content. | 2021-07-01 |
20210201045 | MULTIMEDIA CONTENT SUMMARIZATION METHOD AND SYSTEM THEREOF - A method and system for summarizing multimedia content is disclosed. The method includes the steps of extracting a set of video files from a multimedia content such that each of the set of video files comprises a plurality of frames, and summarizing each of the set of video files to generate a set of summarized video files. Summarizing includes modifying a number of frames in each of the set of video files while retaining a caption generated for each of the set of video files. The method further includes generating sets of bridge frames for the set of summarized video files, based on a deep learning model. A set of bridge frames from the sets of bridge frames maintains continuity between corresponding adjacent summarized video files. The method includes generating a summarized multimedia content based on the set of summarized video files and the sets of bridge frames. | 2021-07-01 |
20210201046 | METHOD AND APPARATUS FOR DATA PROCESSING, AND METHOD AND APPARATUS FOR VIDEO COVER GENERATION - Embodiments of the disclosure provides methods and apparatuses for data processing and video cover generation. The method for video cover generation comprises: receiving a video for processing, a processing request for the video, and a video cover generation condition; segmenting the video based on the processing request to obtain a sequence of target clips; scoring target clips in the sequence of target clips based on a pre-configured algorithm to obtain scores for the target clips; after weighting the scores of target clips satisfying the video cover generation condition, weighting the scores of target clips associated with a video category of the video; and generating, based on a weighting process result, a personalized video cover attracting more user attention. | 2021-07-01 |
20210201047 | VIDEO SUMMARIZATION USING SEMANTIC INFORMATION - Example apparatus disclosed herein are to process a first image of a first video segment from the image capture sensor with a machine learning algorithm to determine a first score for the first image, the machine learning algorithm to detect actions associated with images, the actions associated with labels. Disclosed example apparatus are also to determine a second score for the first video segment based on respective first scores for corresponding images in the first video segment. Disclosed example apparatus are further to determine, based on the second score, whether to retain the first video segment in the memory. | 2021-07-01 |
20210201048 | Nighttime Sensing - Systems and methods for night vision combining sensor image types. Some implementations may include obtaining a long wave infrared image from a long wave infrared sensor; detecting an object in the long wave infrared image; identifying a region of interest associated with the object; adjusting a control parameter of a near infrared sensor based on data associated with the region of interest; obtaining a near infrared image captured using the adjusted control parameter of the near infrared sensor; and determining a classification of the object based on data of the near infrared image associated with the region of interest. | 2021-07-01 |
20210201049 | VEHICULAR VISION SYSTEM WITH ENHANCED RANGE FOR PEDESTRIAN DETECTION - A vision system for a vehicle includes a camera and an electronic control unit (ECU) with an image processor. The ECU generates a reduced resolution frame of captured image data and the ECU determines a reduced resolution detection result based on pedestrian detection using the reduced resolution frame of captured image data. The ECU, responsive to processing by the image processor of image data, generates a cropped frame of captured image data and the ECU determines a cropped detection result based on pedestrian detection using the cropped frame of captured image data. Responsive to determining the reduced resolution detection result and determining the cropped detection result, the ECU merges the reduced resolution detection result and the cropped detection result into a final pedestrian detection result. The final pedestrian detection result is indicative of presence of a pedestrian within the field of view of the camera. | 2021-07-01 |
20210201050 | GENERATING TRAINING DATA FROM OVERHEAD VIEW IMAGES - The present invention relates to a method of generating an overhead view image of an area. More particularly, the present invention relates to a method of generating a contextual multi-image based overhead view image of an area using ground map data and field of view image data. | 2021-07-01 |
20210201051 | LANE SELECTION USING MACHINE LEARNING - To selecting a lane in a multi-lane road segment for a vehicle travelling on the road segment, a system determines current traffic information for the road segment including a plurality of lanes and applies the current traffic information to a machine learning (ML) model to generate an indication of one of the plurality of lanes in which the vehicle is to travel. Subsequently to the vehicle selecting the indicated lane, the system determines an amount of time the vehicle took to travel a certain distance following the selection, and provides the determined amount of time to the ML model as a feedback signal. | 2021-07-01 |
20210201052 | METHOD AND APPARATUS FOR PREDICTING INTENT OF VULNERABLE ROAD USERS - Techniques are described for estimating intentions of pedestrians and other road users in vicinity of a vehicle. In certain embodiments, the techniques comprise obtaining, by a computer system of a vehicle equipped with one or more sensors, a sequence of video frames corresponding to a scene external to the vehicle, detecting one or more vulnerable road users (VRUs) in the sequence of video frames, wherein the detecting comprises estimating pose of each of the detected one or more VRUs. The techniques further include generating a segmentation map of the scene using one or more of the video frames; estimating one or more intention probabilities using estimated pose of the one or more VRUs and the segmentation map, each intention probability corresponding to one of the detected one or more VRUs, and adjusting one or more automated driving actions based on the estimated one or more intention probabilities. | 2021-07-01 |
20210201053 | VISUAL ANALYTICS PLATFORM FOR UPDATING OBJECT DETECTION MODELS IN AUTONOMOUS DRIVING APPLICATIONS - Visual analytics tool for updating object detection models in autonomous driving applications. In one embodiment, an object detection model analysis system including a computer and an interface device. The interface device includes a display device. The computer includes an electronic processor that is configured to extract object information from image data with a first object detection model, extract characteristics of objects from metadata associated with image data, generate a summary of the object information and the characteristics, generate coordinated visualizations based on the summary and the characteristics, generate a recommendation graphical user interface element based on the coordinated visualizations and a first one or more user inputs, and update the first object detection model based at least in part on a classification of one or more individual objects as an actual weakness in the first object detection model to generate a second object detection model for autonomous driving. | 2021-07-01 |
20210201054 | Close-in Sensing Camera System - The technology relates to an exterior sensor system for a vehicle configured to operate in an autonomous driving mode. The technology includes a close-in sensing (CIS) camera system to address blind spots around the vehicle. The CIS system is used to detect objects within a few meters of the vehicle. Based on object classification, the system is able to make real-time driving decisions. Classification is enhanced by employing cameras in conjunction with lidar sensors. The specific arrangement of multiple sensors in a single sensor housing is also important to object detection and classification. Thus, the positioning of the sensors and support components are selected to avoid occlusion and to otherwise prevent interference between the various sensor housing elements. | 2021-07-01 |
20210201055 | SYSTEMS AND METHODS FOR COMPUTER-BASED LABELING OF SENSOR DATA CAPTURED BY A VEHICLE - Examples disclosed herein may involve (i) based on an analysis of 2D data captured by a vehicle while operating in a real-world environment during a window of time, generating a 2D track for at least one object detected in the environment comprising one or more 2D labels representative of the object, (ii) for the object detected in the environment: (a) using the 2D track to identify, within a 3D point cloud representative of the environment, 3D data points associated with the object, and (b) based on the 3D data points, generating a 3D track for the object that comprises one or more 3D labels representative of the object, and (iii) based on the 3D point cloud and the 3D track, generating a time-aggregated, 3D visualization of the environment in which the vehicle was operating during the window of time that includes at least one 3D label for the object. | 2021-07-01 |
20210201056 | VEHICULAR SYSTEM FOR TESTING PERFORMANCE OF OBJECT DETECTION ALGORITHMS - A method for testing a vehicular driving assist system includes positioning the vehicle near a target object such that the target object is within a field of sensing of at least one sensor of the vehicle. The vehicle has an ECU having electronic circuitry and associated software, with the electronic circuitry of the ECU including a processor for processing data captured by the at least one sensor to detect presence of objects in the field of sensing of the at least one sensor. The vehicle is maneuvered away from the target object and, as the vehicle maneuvers away from the target object, the data captured by the at least one sensor is recorded. The recorded data is reversed to indicate the vehicle is approaching the target object. The reversed recorded data is provided as an input to the vehicular driving assist system to test the vehicular driving assist system. | 2021-07-01 |
20210201057 | TRAFFIC LIGHT RECOGNITION SYSTEM AND METHOD THEREOF - A traffic light recognition system including a map, a localization module, at least one image capturing device and an image processing module is provided. The map is configured to provide an information relevant to a traffic light. The localization module is configured to provide a positioning information relevant to the traffic light. At least one image capturing device is configured to capture a real-time road image relevant to the traffic light. The image processing module is configured to combine the map and the positioning information of the traffic light provided by the localization module to generate a region of interest in the real-time road image captured by the image capturing device, and to recognize the traffic light in the region of interest, wherein the traffic light includes a light box and at least one light signal. | 2021-07-01 |
20210201058 | METHOD OF AND SYSTEM FOR DETERMINING TRAFFIC SIGNAL STATE - There is disclosed a method and system for determining a predicted state of a traffic signal. A video of the traffic signal is received. Still images of the traffic signal are generated based on the video. A first machine learning algorithm (MLA) outputs a vector for each bulb in each still image, the vector indicating a predicted status of the bulb. A second MLA determines a predicted state of the traffic signal based on the vectors. | 2021-07-01 |
20210201059 | DRIVER CONDITION ESTIMATING DEVICE, DRIVER CONDITION ESTIMATING METHOD AND COMPUTER PROGRAM THEREFOR - A driver condition estimating device includes circuitry configured to measure movement of the head of a driver from output of a driver camera and detect a sign of abnormality of the driver from the movement of the head. The circuitry is configured to calculate a periodic feature amount from time series data showing the movement of the head of the driver, calculate a time series variation pattern from the obtained periodic feature amount, and compare the obtained time series variation pattern with a predetermined threshold to determine existence of the sign of abnormality of the driver. | 2021-07-01 |
20210201060 | METHOD OF HOST-DIRECTED ILLUMINATION AND SYSTEM FOR CONDUCTING HOST-DIRECTED ILLUMINATION - A method of host-directed illumination for verifying the validity of biometric data of a user is provided that includes capturing biometric data from a user with an authentication device during authentication and directing illumination of the biometric data from a host authentication system during the capturing operation. Moreover, the method includes comparing illumination characteristics of the captured biometric data against illumination characteristics expected to result from the directing operation, and determining that the user is a live user when the illumination characteristics of the captured biometric data match the illumination characteristics expected to result from the directing operation. | 2021-07-01 |
20210201061 | INTELLIGENT GALLERY MANAGEMENT FOR BIOMETRICS - A system provides intelligent gallery management for biometrics. A first gallery is obtained that includes biometric and/or other information on a population of people. An application is identified. A subset of the population of people is identified based on the application. A second gallery is derived from the first gallery by pulling the information for the subset of the population of people without pulling the information for the population of people not in the subset. Biometric identification (such as facial recognition) for the application may then be performed using the second gallery rather than the first gallery. In this way, the system is improved as less time is required for biometric identification, fewer device resources are used, and so on. | 2021-07-01 |
20210201062 | METHOD AND SYSTEM FOR IMPROVING MULTI-THREADED FACE RECOGNITION ACCURACY - The present application discloses a method and a system for improving multi-threaded face recognition accuracy. The method includes: acquiring an initial image; performing a face extraction on the initial image in the first CPU to obtain a face image; performing a feature extraction on the face image in the second CPU, and transmitting the facial features extracted by the feature extraction to the first CPU for a face feature comparison; outputting the face feature comparison result, after the second CPU extracts the face features in the face image, and the first CPU performs the face feature comparison according to the face features. | 2021-07-01 |
20210201063 | DRIVE METHOD FOR TEXTURE RECOGNITION DEVICE AND TEXTURE RECOGNITION DEVICE - A drive method for a texture recognition device and a texture recognition device. The texture recognition device includes a light source array and an image sensor array. The image sensor array includes a plurality of image sensors, the plurality of image sensors are configured to receive light emitted from the plurality of sub-light sources and then reflected by a texture to the plurality of image sensors for a texture collection; the drive method includes: at a first moment, the light source array operating to provide a first photosensitive light source, and at the first moment or a second moment different from the first moment, the light source array operating to provide a second photosensitive light source. A first imaging range of the first photosensitive light source on the image sensor array partially overlaps a second imaging range of the second photosensitive light source on the image sensor array. | 2021-07-01 |
20210201064 | METHOD, DEVICE, AND COMPUTER READABLE STORAGE MEDIUM FOR RECOGNIZING MIXED TYPESET TEXTS - The present disclosure provides a method, a device, and a computer readable storage medium for recognizing mixed typeset texts. The method includes: detecting one or more bounding boxes each containing a text paragraph from a picture; determining a text typesetting direction of each bounding box based on geometric characteristics of the bounding box, where the text typesetting direction includes horizontal and vertical; and inputting the bounding box into a text recognition network corresponding to the text typesetting direction, based on the text typesetting direction of the bounding box, to recognize texts in the bounding box. | 2021-07-01 |
20210201065 | IMAGE PROCESSING APPARATUS FOR CHARACTER RECOGNITION, CONTROL METHOD OF THE SAME, STORAGE MEDIUM AND IMAGE PROCESSING SYSTEM - An image processing apparatus acquires a plurality of captured images of characters captured in time series, each of the characters including a plurality of segments, recognize the characters captured for each of the plurality of captured images, and determine which one of the characters recognized from each of the plurality of captured images is to be output. The image processing apparatus determines, in accordance with a change aspect in time series of the characters recognized from each of the plurality of captured images, which one of the characters recognized from each of the plurality of captured images is to be output. | 2021-07-01 |
20210201066 | SYSTEMS AND METHODS FOR DISPLAYING REGION OF INTEREST ON MULTI-PLANE RECONSTRUCTION IMAGE - A method for image processing may be provided. The method may include obtaining a 3D image of a subject and an ROI within the subject. The method may also include generating a 3D segmentation image relating to the ROI of the subject based on the 3D image. The method may also include selecting an MPR plane from the 3D image. The method may further include determining a target 2D image of the MPR plane based on the 3D image and the 3D segmentation image. The target 2D image of the MPR plane may include a bounding box annotating the ROI on the MPR plane. | 2021-07-01 |
20210201067 | OPTICAL OVERLAY DEVICE - Devices and methods for visibly highlighting areas of a region including an imager configured to image the region with a sensitivity to at least one of wavelength, light level, or contrast greater than the human eye, an overlay element configured to visibly highlight areas of the region and registered to the imager to produce alignment of imaged features with highlighted features at the same location on the region, and at least one of a controller executing a program or logic configured to process acquired images from the imager to identify areas of the region determined not visible to the human eye, and control the overlay element to visibly highlight those areas on the region. | 2021-07-01 |
20210201068 | IMAGE PROCESSING METHOD AND APPARATUS, AND ELECTRONIC DEVICE - Embodiments of the present disclosure disclose an image processing method and apparatus, and an electronic device. The method includes: obtaining a key frame image that includes a target object, and obtaining a to-be-processed frame image that includes the target object; extracting a feature point in the key frame image and a feature point in the to-be-processed frame image, respectively; determining a matching relationship between each feature point in the key frame image and each feature point in the to-be-processed frame image; determining a transformation relationship based on the feature point in the key frame image and a feature point in the to-be-processed frame image that matches the feature point in the key frame image; and processing the to-be-processed frame image based on the transformation relationship to obtain a target frame image. | 2021-07-01 |
20210201069 | IMAGE PROCESSING SYSTEM, IMAGE PROCESSING METHOD, AND PROGRAM - An image processing system having at least one processor configured to: obtain a captured image of a document that includes a fixed part and an un-fixed part, the document being captured by an image reader or an image capture device; detect a feature part of the fixed part based on the captured image; obtain, in a case where the feature part is detected, a shaped image of the captured image such that a positional relationship of the feature part is aligned with a predetermined first positional relationship; and search for, in a case where the feature part is not detected, a substitute feature part of the fixed part based on the captured image, wherein in a case where the feature part is not detected, the at least one processor obtains the shaped image such that a position of the substitute feature part is aligned with a predetermined second position. | 2021-07-01 |
20210201070 | SYSTEMS AND METHODS FOR SEMANTIC MAP-BASED ADAPTIVE AUTO-EXPOSURE - In one embodiment, a method includes receiving sensor data of an environment of the vehicle generated by one or more sensors of the vehicle, the sensors comprising a camera, identifying, based on the sensor data, one or more objects in a field of view of the camera and one or more object types that correspond to the one or more objects, determining one or more target histograms that correspond to the object types, generating a processed image based on an image captured by the camera, wherein the processed image has a histogram based on the target histograms, and using the processed image to determine state information associated with the objects. The processed image may be generated by processing the image captured by the camera using a histogram matching algorithm to generate the histogram of the processed image based on the target histograms. | 2021-07-01 |
20210201071 | IMAGE COLORIZATION BASED ON REFERENCE INFORMATION - According to implementations of the subject matter described herein, there is provided an image colorization solution. The solution includes determining a similarity between contents presented in a grayscale source image and a color reference image and determining a col or target image corresponding to the source image based on the similarity. Specifically, a first and a second sets of blocks similar and dissimilar to the reference image are determined based on the similarity; a first color for the first set of blocks is determined based on a color of corresponding blocks in the reference image; a second color for the second set of blocks is determined independently of the reference image. Through this solution, it is possible to provide user controllability and customized effects in colorization, and there is no strict requirement on correspondence between the color image and grayscale image, achieving more robustness to selection of color reference images. | 2021-07-01 |
20210201072 | PHOTOSET CLUSTERING - Indexing a photoset for retrieval of representative photos of an event is disclosed. Photos of a photoset are clustered into taxa of a hierarchical event taxonomy. A representative photo from each taxa is selected based on an object image quality. | 2021-07-01 |
20210201073 | IMAGE ENCODING METHOD AND DEVICE AND COMPUTER-READABLE STORAGE MEDIUM - Embodiments of the present disclosure provide an image encoding method and device, and a computer-readable storage medium. The method includes: obtaining a to-be-encoded image set, where the to-be-encoded image set includes at least one to-be-encoded image; extracting feature information of each to-be-encoded image by using a preset feature extraction model, to obtain image feature information; determining an encoding parameter corresponding to the image feature information; and sending the encoding parameter to an image encoder, so that the image encoder performs an encoding operation on the to-be-encoded image based on the encoding parameter. Therefore, the to-be-encoded image can be automatically encoded, image encoding efficiency is effectively improved, and human resources can be saved. | 2021-07-01 |
20210201074 | METHOD AND SYSTEM FOR DETECTING CONCEALED OBJECTS USING HANDHELD THERMAL IMAGER - A method of detecting concealed objects using a thermal imager includes obtaining an output comprising a plurality of pixels representing a person, analyzing each pixel matching a contour of the person and excluding any pixel within a blob bounding box of the person, and determining whether a pixel address is represented in a pixel map. In addition, the method includes comparing a value of each remaining pixel to an allowable minimum threshold value representing a lower pre-defined body temperature, and comparing the value of each remaining pixel greater than or equal to the allowable minimum threshold value to an upper allowable threshold value representing an upper pre-defined body temperature. The method also includes excluding any of the remaining pixels within a range between the lower and upper pre-defined body temperatures to define final set of pixels and calculating a pixel difference to indicate a severity of the difference. | 2021-07-01 |
20210201075 | LOW-SHOT LEARNING FROM IMAGINARY 3D MODEL - In one aspect, there is provided a system including at least one data processor and at least one memory. The at least one memory may store instructions that cause operations when executed by the at least one data processor. The operations may include retrieving a set of authentic base class images from a database. The operations may further include generating, based on the set of authentic base class images, a three dimensional mesh of the base class. The operations may further include retrieving a set of authentic novel class images. The operations may further include generating, at a first neural network and based on the three dimensional mesh and the set of authentic novel class images, a set of synthetic novel class images. The operations may further include training a second neural network based on the set of synthetic novel class images. | 2021-07-01 |
20210201076 | ONTOLOGY MATCHING BASED ON WEAK SUPERVISION - A method is for matching a set of first classes assigned to a first data set with a set of second classes assigned to a second data set. The method includes constructing, via a set of pre-processing functions, a plurality of alignment profiles such that at least one alignment profile is assigned to each of the first classes and each of the second classes. The method includes generating a comparison matrix for each group of the alignment profiles, such that each group includes at least one of the first classes and at least one of the second classes. The method includes training a first machine learning model, through supervised training, based on the generated comparison matrices and based on probabilistic labels generated by a second machine learning model. | 2021-07-01 |
20210201077 | SYSTEMS AND METHODS FOR CREATING TRAINING DATA - Training images can be synthesized in order to obtain enough data to train a model (e.g., a neural network) to recognize various classifications of a type of object. Images can be synthesized by blending images of objects labeled using those classifications into selected background images. To improve results, one or more operations are performed to determine whether the synthesized images can still be used as training data, such as by verifying one or more objects of interested represented in those images is not occluded, or at least satisfies a threshold level of acceptance. The training images can be used with real world images to train the model. | 2021-07-01 |
20210201078 | METHODS AND SYSTEMS FOR ADVANCED AND AUGMENTED TRAINING OF DEEP NEURAL NETWORKS USING SYNTHETIC DATA AND INNOVATIVE GENERATIVE NETWORKS - Methods and systems for advanced and augmented training of deep neural networks (DNNs) using synthetic data and innovative generative networks. A method includes training a DNN using synthetic data, training a plurality of DNNs using context data, associating features of the DNNs trained using context data with features of the DNN trained with synthetic data, and generating an augmented DNN using the associated features. | 2021-07-01 |
20210201079 | TRAINING DATA GENERATION METHOD AND INFORMATION PROCESSING APPARATUS - A non-transitory computer-readable recording medium has stored therein a program that causes a computer to execute a process comprising: acquiring a first feature from a machine learning model that estimates a first result of a target after a first period in response to an input of a first chronological state of the target in the first period, the first feature being a feature of the first chronological state; acquiring a second feature by inputting a second chronological state to the machine learning model, the second feature being a feature of the second chronological state in a second period including a period after the first result is determined; and generating, based on the first feature and the second feature, training data that takes the second chronological state as an explanatory variable and takes a second result as an objective variable, the second result being obtained by changing the determined first result. | 2021-07-01 |
20210201080 | LEARNING DATA CREATION APPARATUS, METHOD, PROGRAM, AND MEDICAL IMAGE RECOGNITION APPARATUS - A learning data creation apparatus, a method, a program, and a medical image recognition apparatus efficiently creating learning data for performing machine learning on a learning model that recognizes a size of a target region included in a medical image are provided. | 2021-07-01 |
20210201081 | DATA LABELING METHOD, APPARATUS AND SYSTEM - A data labeling method, apparatus and system are provided. The method includes: sampling a data source according to an evaluation task for the data source to obtain sampled data; generating a labeling task from the sampled data; sending the labeling task to a labeling device; and receiving a labeled result of the labeling task from the labeling device. As such, an automatic evaluation of data can be implemented by using the evaluation task, and evaluation efficiency is improved. | 2021-07-01 |
20210201082 | METHOD AND SYSTEM FOR TRAINING ARTIFICIAL NEURAL NETWORK BASED IMAGE CLASSIFIER USING CLASS-SPECIFIC RELEVANT FEATURES - The disclosure relates to method and system for training an artificial neural network (ANN) based image classifier using class-specific relevant features. The method includes receiving the ANN based image classifier, training image dataset, and various features of the training image dataset. The method further includes determining a relative relevance value of each of the features corresponding to each of the classes based on the ANN based image classifier, segregating co-occurring features from the features for each of the classes based on the training image dataset and the ANN based image classifier, identifying an imbalance in the class-specific relevant features for each of the classes based on the relative relevance value of each of the features corresponding to each of the classes, and updating the ANN based image classifier based on the imbalance in the class-specific relevant features and the co-occurring features for each of the classes. | 2021-07-01 |
20210201083 | VEHICLE-MOUNTED DEVICE AND METHOD FOR TRAINING OBJECT RECOGNITION MODEL - A method of training an object recognition model includes obtaining a sample set. The sample set is divided into a training set and a verification set. The object recognition model is obtained by training a neural network using the training set, and the object recognition model is verified using the verification set. | 2021-07-01 |
20210201084 | REINFORCEMENT LEARNING-BASED SENSOR DATA MANAGEMENT METHOD AND SYSTEM - A reinforcement learning-based sensor data management system includes a processor configured to: manage virtualized objects that correspond to sensors included in a sensor network to update data received from each sensor and queries representing a data quality requested by an application; calculate an abstracted action that abstracts a size of an action space of the sensor network based on present state information of the virtualized objects and the queries; calculate scores for virtualized objects based on position relationships between the calculated abstracted action the virtualized objects; and assign priorities to the virtualized objects based on the calculated scores to update data received from the sensors to the virtualized objects according to the priorities. | 2021-07-01 |
20210201085 | VEHICULAR SYSTEM FOR TESTING PERFORMANCE OF HEADLAMP DETECTION SYSTEMS - A method for testing a vehicular driving assist system includes providing a neural network and training the neural network using a database of images, with each image of the database of images including an image of a headlight or a taillight of a vehicle. The trained neural network is provided with an input image that does not include a headlight or a taillight. The neural network, using the input image, generates an output image, with the output image including an image of a headlight or taillight generated by the neural network. The output image is provided as an input to the driving assist system to test the driving assist system. | 2021-07-01 |
20210201086 | TRAINING METHOD AND SYSTEM OF OBJECTS DETECTION MODEL BASED ON ADAPTIVE ANNOTATION DESIGN - A training system and method of object detection model is disclosed. The training system includes an object detection model and a loss calculation module. The object detection model is configured to generate an output image according to an input image. The loss calculation module, coupled to the object detection model, is configured to calculate a total classification loss value according to the output image and a solution image, calculate a loss value according to the total classification loss value, and transmit the loss value to the object detection model. The total classification loss value is calculated according to a number of classification losses corresponding to a number of object types. Each classification loss corresponding to each object type is calculated according to a first parameter, a second parameter and a third parameter. | 2021-07-01 |
20210201087 | ERROR JUDGMENT APPARATUS, ERROR JUDGMENT METHOD AND PROGRAM - An error determination apparatus includes a classification estimation process observation unit configured to acquire data in an estimation process from a classification estimation unit for estimating a classification of classification object data and generate a feature vector based on the data, and an error determination unit configured to receive the feature vector generated by the classification estimation process observation unit and a classification result output from the classification estimation unit and determine whether the classification result is correct based on the feature vector and the classification result. | 2021-07-01 |
20210201088 | IMAGE CLASSIFICATION SYSTEM AND METHOD - An image classification system includes a storage device, a computing device and a first processing device. The storage device stores a plurality of pseudo-centroid datasets, wherein the pseudo-centroid datasets correspond to a plurality of units of first image dataset, and the number of pseudo-centroid data points of each of the pseudo-centroid datasets is much smaller than the number of data points of each of the units of first image dataset. The computing device receives the second image data and computes a plurality of feature values of the second image data. The first processing device receives the feature values and the pseudo-centroid datasets, and compares the feature values with the pseudo-centroid data points to identify and classify the second image data. | 2021-07-01 |
20210201089 | METHOD AND DEVICE FOR DETERMINING WHETHER OBJECT INCLUDES DEFECT - A method and device for determining whether an object includes a defect are provided. The method includes the following steps. A tested image of a tested object is obtained. Selected good product sample data corresponding to the tested object is obtained. A dissimilarity value between the tested image and the selected good product sample data is calculated by using a dissimilarity model, and whether the tested object is a good product or a defective product is determined according to the dissimilarity value. | 2021-07-01 |
20210201090 | METHOD AND APPARATUS FOR IMAGE PROCESSING AND IMAGE CLASSIFICATION - The present disclosure provides methods and apparatuses for image processing and image classification. In one embodiment, the method for image processing comprises: receiving an image; obtaining a first classification result for the image based on a classification model; processing the image for classification based on a preset process, and providing a processing result into a re-ranking model to obtain a second classification result for the image; and determining a target classification result for the image, based on the first classification result and the second classification result. | 2021-07-01 |
20210201091 | SYSTEM AND METHOD FOR ADAPTIVE FUSION OF DATA FROM MULTIPLE SENSORS USING CONTEXT-SWITCHING ALGORITHM - The present disclosure is directed to systems and method for adaptive fusion of sensor data from multiple sensors. The method comprises: collecting sensor data generated by a plurality of sensors in an environment; determining the quality of the sensor data generated by each sensor of the plurality of sensors, the quality metric corresponding to a suitability of the sensor data for performing a given task; selecting, via an assessment artificial intelligence program, one or more sensors from the plurality of sensors based on the determined quality metric of the sensor data that yields a desired accuracy for performing the given task; and selecting for each sensor of the plurality of sensors selected, via the assessment artificial intelligence program, a machine learning algorithm from a predetermined set of machine learning algorithms based on the determined quality metric of the sensor data that yields the desired accuracy for performing the given task. | 2021-07-01 |
20210201092 | PROCESSING IMAGES USING DEEP NEURAL NETWORKS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image. | 2021-07-01 |
20210201093 | CROSS-DOMAIN IMAGE COMPARISON METHOD AND SYSTEM - A cross-domain image comparison method and a cross-domain image comparison system are provided. The cross-domain image comparison method includes the following steps. Two videos in cross-domain are obtained. The videos are generated by different types of devices. A plurality of semantic segmentation areas are obtained from one frame of each of the videos. A region of interest pair (ROI pair) is obtained according to moving paths of the semantic segmentation areas in the videos. Two bounding boxes and two central points of the ROI pair are obtained. A similarity between the frames is obtained according to the bounding boxes and the central points. | 2021-07-01 |
20210201094 | METHODS AND APPARATUS FOR IDENTIFYING OBJECTS DEPICTED IN A VIDEO USING EXTRACTED VIDEO FRAMES IN COMBINATION WITH A REVERSE IMAGE SEARCH ENGINE - Example systems disclosed herein are to process image frames with a reverse image search engine to generate corresponding search results pages, capture screenshots corresponding respectively to the search results pages, generate base query records corresponding to respective ones of the screenshots that have respective textual information that matches a base search term, the respective ones of the base query records including the base search term and at least portions of the respective textual information from the corresponding screenshots, determine an object search term based on a frequency analysis of the textual information included in the base query records, generate object query records corresponding respectively to ones of the base query records that have respective textual information matching the object search term, and identify a first object depicted in the video based on at least one criteria applied to the object query records. | 2021-07-01 |
20210201095 | IMAGE PROCESSING DEVICE, PRINTING APPARATUS, AND IMAGE PROCESSING METHOD - An image processing device configured to generate printing image data used during printing from input image data including a bar code constituted by a bar element and a space element that are a plurality of elements arranged based on a predetermined standard, includes a frequency distribution calculation unit configured to acquire widths of the plurality of elements respectively to calculate a frequency distribution of the widths of the plurality of elements, a standard width determination unit configured to determine a standard width of the plurality of elements of the barcode in the printing image data using the frequency distribution, and a correction unit configured to correct the widths of the plurality of elements of the barcode in the printing image data to the standard width. | 2021-07-01 |
20210201096 | COMMUNICATION SYSTEM, NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM STORING PROGRAM FOR INFORMATION PROCESSING APPARATUS, AND PRINTER - A communication system includes an information processing apparatus and a printer. A controller of the information processing apparatus is configured to receive a layout instruction, generate image data representing a layout image including a first object and a second object, generate edit order data indicating an edit order of the first object and the second object, and send the image data and the edit order data to the printer. A controller of the printer is configured to edit the received image data in accordance with the received edit order data, and activate the printer engine to form the layout image based on the edited image data. | 2021-07-01 |
20210201097 | IMAGE FORMING APPARATUS AND IMAGE FORMING METHOD TO VERIFY TARGET IMAGE USING CORRECTED IMAGE - A correct image and print settings are registered in association with each other, the registered correct image is selected based on print settings of a verification target image, and verification is performed by comparing the verification target image with the selected correct image. | 2021-07-01 |
20210201098 | DETECTION OF IMAGES IN RELATION TO TARGETS BASED ON COLORSPACE TRANSFORMATION TECHNIQUES AND UTILIZING INFRARED LIGHT - Techniques to improve detection and security of images, including formation and detection of matrix-based images. Some techniques include logic to process image data, generate one or more colorspaces associated with that data, and perform colorspace conversions based on the generated colorspace. The logic may be further configured to generate an image based on the colorspace conversions, including but not limited to a matrix bar code. The logic may be further configured to apply one or both of an ultraviolet layer and an infrared layer to the image, e.g. matrix barcode, generated from the colorspace conversion(s). Other embodiments are described and claimed. | 2021-07-01 |
20210201099 | DETECTION OF IMAGES IN RELATION TO TARGETS BASED ON COLORSPACE TRANSFORMATION TECHNIQUES AND UTILIZING ULTRAVIOLET AND INFRARED LIGHT - Techniques to improve detection and security of images, including formation and detection of matrix-based images. Some techniques include logic to process image data, generate one or more colorspaces associated with that data, and perform colorspace conversions based on the generated colorspace. The logic may be further configured to generate an image based on the colorspace conversions, including but not limited to a matrix bar code. The logic may be further configured to apply one or both of an ultraviolet layer and an infrared layer to the image, e.g. matrix barcode, generated from the colorspace conversion(s). Other embodiments are described and claimed. | 2021-07-01 |
20210201100 | Shapeless -- A New Language Concept and Related Technology - Shape Dependent alphabets are error prone and quite imposing on their reader. Proposing “Shapeless”—an alphabet based on the entropic state of a mixture—offering easy, redundant reading. Applications include marking packages for shipping and industrial handling, signing items to hinder fraud, offering alternative communication channels, and analyzing video streams for changes of interest. | 2021-07-01 |
20210201101 | Alternative Identification Of Objects For Constrained Networks - A system for assigning alternative identification to objects can include a first communication device of a first object, where the first communication device broadcasts a first communication signal that includes a first identification of the first object. The system can also include a first electrical device having a first receiver and a first transmitter, where the first receiver receives the first communication signal. The system can further include a controller communicably coupled to the first electrical device, where the controller retrieves the first identification of the first communication device from the first communication signal, assigns a first alternative identification to the first communication device based on the first identification, saves the first identification and the first alternative identification of the first object in a first table, and sends a second communication signal that includes the first alternative identification and the first identification of the first object. | 2021-07-01 |
20210201102 | FLEXIBLE RADIO FREQUENCY IDENTIFICATION TAGS - Flexible, stretchable RFID tags are formed by a pocket that is formed from one or more substrates and layers of adhesive, and an electronic circuit that is located within this pocket. The RFID tags can include a stretchable substrate and an electronic circuit attached to the stretchable substrate by one or a finite number of discrete spaced apart attachment locations. When the pocket is formed by relatively thick adhesive layers adhering together one or more flexible substrates to form an internal cavity, the electronic circuit is located within this cavity and either is not adhered to any of the substrates of the cavity, and is free to move about within the cavity, or the electronic circuit can be attached to a substrate by a thin layer of adhesive. | 2021-07-01 |
20210201103 | METHOD FOR MANUFACTURING A MICROCHIP SUPPORT WITH A SURFACE EFFECT - The invention relates to a method for producing a support body in a card format, with a graphic customization, that has a surface finishing effect that is more or less smooth, rough, mirrored or matte on the support body. The method includes supplying a support body having a layer of material configured to allow a marking by punching or lamination. The layer is exposed on the main external face and the surface finishing effect is equivalent to that obtained by a step of marking or lamination while not including a step of depositing varnish. | 2021-07-01 |
20210201104 | CONTACTLESS CARD AND METHOD OF ASSEMBLY - A method of forming a contactless transaction card. The method may include providing a card body, defining a window, and attaching an antenna assembly layer to the card body, where the antenna assembly layer includes an antenna, a set of curable connectors, disposed on a set of end regions of the antenna within the window, and a UV-transparent layer, supporting the antenna. The method may include providing a contactless chip module within the window on a first side of the antenna assembly layer, and directing radiation through the UV-transparent layer, wherein the contactless chip module is electrically connected to the antenna via the curable connectors. | 2021-07-01 |
20210201105 | COMMODITY REGISTRATION SUPPORTING DEVICE AND COMPUTER PROGRAM - A commodity registration supporting device according to an embodiment includes a receiver, an acquiring section, a first detecting section, an adding section, and an output section. The receiver receives an electromagnetic wave transmitted from a first transmitter provided in a display place where a commodity is displayed. The acquiring section acquires, from the electromagnetic wave received by the receiver, identification information of the commodity displayed in the display place where the first transmitter that transmits the electromagnetic wave is provided. The first detecting section detects a first act of a purchaser taking out the commodity from the display place and storing the commodity in a storage body. The adding section adds, if first act is detected by the first detecting section, the commodity identified by the identification information acquired by the acquiring section to a list. The output section outputs the list. | 2021-07-01 |
20210201106 | BIOLOGICAL SAMPLE STORAGE CONTAINER AND DUAL CHIP WIRELESS IDENTIFICATION TAG THEREOF - A biological sample storage container and a dual chip wireless identification tag thereof are provided. The dual chip wireless identification tag includes a substrate, an antenna structure, a first chip, and a second chip. The antenna structure is disposed on the substrate, and includes two radiation parts and two matching parts. The two matching parts are connected between the two radiation parts, the first chip is coupled to one of the matching parts, and the second chip is coupled to the other one of the matching parts. | 2021-07-01 |
20210201107 | NEURAL ARCHITECTURE SEARCH BASED ON SYNAPTIC CONNECTIVITY GRAPHS - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting a neural network architecture for performing a machine learning task. In one aspect, a method comprises: obtaining data defining a synaptic connectivity graph representing synaptic connectivity between neurons in a brain of a biological organism; generating data defining a plurality of candidate graphs based on the synaptic connectivity graph; determining, for each candidate graph, a performance measure on a machine learning task of a neural network having a neural network architecture that is specified by the candidate graph; and selecting a final neural network architecture for performing the machine learning task based on the performance measures. | 2021-07-01 |
20210201108 | MODEL WITH MULTIPLE CONCURRENT TIMESCALES - In one implementation, a method of generating an environment state is performed by a device including one or more processors and non-transitory memory. The method includes obtaining a first environment state of an environment, wherein the first environment state indicates the inclusion in the environment of a first asset associated with a first timescale value and a second asset associated with a second timescale value, wherein the first environment state further indicates that the first asset has a first state of the first asset and the second asset has a first state of the second asset. The method includes determining a second state of the first asset and the second asset based on the first and second timescale value. The method includes determining a second environment state that indicates that the first asset has the second state and the second asset has the second state. | 2021-07-01 |
20210201109 | GRAD NEURAL NETWORKS FOR UNSTRUCTURED DATA - An illustrative embodiment includes a method for analyzing unstructured multidimensional data with a neural network. The method includes designing the neural network at least in part by defining differential operators conforming with dimensions of the data. The method also includes performing forward propagation at a given convolution layer of the neural network at least in part by: obtaining one or more convolved values at least in part by performing convolution over an object within the data, processing respective convolved values to obtain output, and updating the object based at least in part on the output. | 2021-07-01 |
20210201110 | METHODS AND SYSTEMS FOR PERFORMING INFERENCE WITH A NEURAL NETWORK - The present disclosure provides methods, systems, and non-transitory computer readable media for performing inference with a neural network. The systems include one or more processing units configured to instantiate a neural network comprising a bypass switch that is associated with at least two bypass networks, wherein each of the at least two bypass networks have at least one hidden layer, the bypass switch is configured to select a bypass network of the at least two bypass networks to activate, and any non-selected bypass network of the at least two bypass networks is not activated. | 2021-07-01 |
20210201111 | PREDICTING NEURON TYPES BASED ON SYNAPTIC CONNECTIVITY GRAPHS - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining an artificial neural network architecture corresponding to a sub-graph of a synaptic connectivity graph. In one aspect, there is provided a method comprising: obtaining data defining a graph representing synaptic connectivity between neurons in a brain of a biological organism; determining, for each node in the graph, a respective set of one or more node features characterizing a structure of the graph relative to the node; identifying a sub-graph of the graph, comprising selecting a proper subset of the nodes in the graph for inclusion in the sub-graph based on the node features of the nodes in the graph; and determining an artificial neural network architecture corresponding to the sub-graph of the graph. | 2021-07-01 |
20210201112 | METHOD OF AND SERVER FOR TRAINING A MACHINE LEARNING ALGORITHM FOR ESTIMATING UNCERTAINTY OF A SEQUENCE OF MODELS - There is provided a method and server for estimating an uncertainty parameter of a sequence of computer-implemented models comprising at least one machine learning algorithm (MLA). A set of labelled digital documents is received, which is to be processed by the sequence of models. For a given model of the sequence of models, at least one of a respective set of input features, a respective set of model-specific features and a respective set of output features are received. The set of predictions output by the sequence of models is received. A second MLA is trained to estimate uncertainty of the sequence of models based on the set of labelled digital documents, and the at least one of the respective set of input features, the respective set of model-specific features, the respective set of output features, and the set of predictions. | 2021-07-01 |
20210201113 | PARALLEL EXECUTION OF GATED ACTIVATION UNIT OPERATIONS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for interleaving matrix operations of a gated activation unit. One of the methods includes receiving a plurality of weight matrices of a gated activation unit of the neural network, the gated activation unit having two or more layers, each layer defining operations comprising: (i) a matrix operation between a weight matrix for the layer and concatenated input vectors and (ii) a nonlinear activation operation using a result of the matrix operation. Rows of the plurality of weight matrices are interleaved by assigning groups of corresponding rows to respective thread blocks, each thread block being a computation unit for execution by an independent processing unit of a plurality of independent processing units of a parallel processing device. | 2021-07-01 |
20210201114 | INTEGRATED SENSING SYSTEM - An integrated sensing system to perform multi-modality sensing of an environment. The integrated sensing system includes a first sensing element that generates a first modality sensing output of the environment, a first edge artificial intelligence (AI) engine that controls the first sensing element and generates a first data analysis result based on the first modality sensing output, a second sensing element that generates a second modality sensing output of the environment, a second edge AI engine that controls the second sensing element and generates a second data analysis result based on the second modality sensing output, and a computer processor that generates, using a central AI algorithm, a classification result of the environment based on the first data analysis result and the second data analysis result, where the computer processor is directly coupled to the first edge AI engine and the second edge AI engine. | 2021-07-01 |
20210201115 | RESERVOIR COMPUTING NEURAL NETWORKS BASED ON SYNAPTIC CONNECTIVITY GRAPHS - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a reservoir computing neural network. In one aspect there is provided a reservoir computing neural network comprising: (i) a brain emulation sub-network, and (ii) a prediction sub-network. The brain emulation sub-network is configured to process the network input in accordance with values of a plurality of brain emulation sub-network parameters to generate an alternative representation of the network input. The prediction sub-network is configured to process the alternative representation of the network input in accordance with values of a plurality of prediction sub-network parameters to generate the network output. The values of the brain emulation sub-network parameters are determined before the reservoir computing neural network is trained and are not adjusting during training of the reservoir computing neural network. | 2021-07-01 |
20210201116 | PROGRESSIVE NEURAL NETWORKS - Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index. | 2021-07-01 |
20210201117 | METHOD AND APPARATUS WITH NEURAL NETWORK PARAMETER QUANTIZATION - A processor-implemented neural network method includes: determining a respective probability density function (PDF) of normalizing a statistical distribution of parameter values, for each channel of each of a plurality of feature maps of a pre-trained neural network; determining, for each channel, a corresponding first quantization range for performing quantization of corresponding parameter values, based on a quantization error and a quantization noise of the respective determined PDF; determining, for each channel, a corresponding second quantization range, based on a signal-to-quantization noise ratio (SQNR) of the respective determined PDF; correcting, for each channel, the corresponding first quantization range based on the corresponding second quantization range; and generating a quantized neural network, based on the corrected first quantization range corresponding for each channel. | 2021-07-01 |
20210201118 | DEEP NEURAL NETWORKS (DNN) HARDWARE ACCELERATOR AND OPERATION METHOD THEREOF - A deep neural network (DNN) hardware accelerator including a processing element array is disclosed. The processing element array includes a processing element array, the processing element array including a plurality of processing element groups and each of the processing element groups including a plurality of processing elements. A first network connection implementation between a first processing element group of the processing element groups and a second processing element group of the processing element groups is different from a second network connection implementation between the processing elements in the first processing element group. | 2021-07-01 |
20210201119 | ARTIFICIAL NEURAL NETWORK ARCHITECTURES BASED ON SYNAPTIC CONNECTIVITY GRAPHS - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an artificial neural network architecture based on a synaptic connectivity graph. According to one aspect, there is provided a method comprising: obtaining a synaptic resolution image of at least a portion of a brain of a biological organism; processing the image to identify: (i) a plurality of neurons in the brain, and (ii) a plurality of synaptic connections between pairs of neurons in the brain; generating data defining a graph representing synaptic connectivity between the neurons in the brain; determining an artificial neural network architecture corresponding to the graph representing the synaptic connectivity between the neurons in the brain; and processing a network input using an artificial neural network having the artificial neural network architecture to generate a network output. | 2021-07-01 |
20210201120 | INFERENCE APPARATUS, CONVOLUTION OPERATION EXECUTION METHOD, AND PROGRAM - An inference apparatus comprises a plurality of PEs (Processing Elements) and a control part. The control part operates a convolution operation in a convolutional neural network using each of a plurality of pieces of input data and a weight group including a plurality of weights corresponding to each of the plurality of pieces of input data by controlling the plurality of PEs. Further, each of the plurality of PEs executes a computation including multiplication of a single piece of the input data by a single weight and also executes multiplication included in the convolution operation using an element with a non-zero value included in each of the plurality of pieces of input data. | 2021-07-01 |
20210201121 | Fiber and Fabric Computers - A fiber computer has a fiber body including electrically insulating fiber body material along the length of the fiber body. Electrical conductors are disposed within the fiber body and are operative to transmit electrical power, electrical ground, clock signals, and data signals through the fiber body. Input units disposed within the fiber body accept external stimuli. Microcontroller microchips disposed within the fiber body process stimuli accepted by an input unit. Memory module microchips within the fiber body store data and communicate with microcontroller microchips. Output units produce an output directed out of the fiber body. A clock signal generator within the fiber body synchronizes operation of input units, microcontroller microchips, memory module microchips, and output units. Each of the computer input units, microcontroller microchips, memory module microchips, and computer output units are disposed in electrical connection with the plurality of electrical conductors for fiber computer operation within the fiber body. | 2021-07-01 |
20210201122 | DATA PROCESSING METHODS, APPARATUSES, DEVICES, STORAGE MEDIA AND PROGRAM PRODUCTS - The present application provides a data processing method, apparatus, device, a storage medium, and a computer program product. The method includes: obtaining to-be-processed data input to a first calculating unit in a plurality of calculating units, wherein the to-be-processed data includes data of a first bit width; obtaining a processing parameter of the first calculating unit, wherein the processing parameter includes a parameter of a second bit width; and obtaining an output result of the first calculating unit based on the to-be-processed data and the processing parameter, wherein a bit width of to-be-processed data input to a second calculating unit in the plurality of calculating units is different from a bit width of the to-be-processed data input to the first calculating unit, and/or a bit width of a processing parameter input to the second calculating unit is different from a bit width of the processing parameter input to the first calculating unit. | 2021-07-01 |
20210201123 | NEURAL NETWORK COMPRISING SPINTRONIC RESONATORS - The invention relates to a neural network comprising:
| 2021-07-01 |
20210201124 | SYSTEMS AND METHODS FOR NEURAL NETWORK CONVOLUTIONAL LAYER MATRIX MULTIPLICATION USING CACHE MEMORY - A computer processor may include a number of cores, a shared cache shared among the cores, and a local cache associated with each core and used by that core only. Input data for a neural network (NN) layer may be partitioned into a set of tiles of size T×T, and the tile set may be partitioned into blocks of R tiles. For each block, a core may perform a transform operation on the tiles to produce transformed data matrices fitting in a local cache, and a set of multiply operations, each multiply operation using a transformed data matrix and a transformed kernel matrix from a set of transformed kernel matrices. The set of transformed kernel matrices may fit in the shared cache. The result of at least one of the multiply operations may be stored in a location used to store a transformed data matrix. | 2021-07-01 |
20210201125 | ON-CHIP TRAINING OF MEMRISTOR CROSSBAR NEUROMORPHIC PROCESSING SYSTEMS - An analog neuromorphic circuit is disclosed having resistive memories that provide a resistance to an input voltage signal as the input voltage signal propagates through the resistive memories generating a first output voltage signal and to provide a resistance to a first error signal that propagates through the resistive memories generating a second output voltage signal. A comparator generates the first error signal that is representative of a difference between the first output voltage signal and the desired output signal and generates the first error signal so that the first error signal propagates back through the plurality of resistive memories. A resistance adjuster adjusts a resistance value associated with each resistive memory based on the first error signal and the second output voltage signal to decrease the difference between the first output voltage signal and the desired output signal. | 2021-07-01 |
20210201126 | OPTOELECTRONIC COMPUTING SYSTEMS - An optoelectronic computing system includes a first semiconductor die having a photonic integrated circuit (PIC) and a second semiconductor die having an electronic integrated circuit (EIC). The PIC includes optical waveguides, in which input values are encoded on respective optical signals carried by the optical waveguides. The PIC includes an optical copying distribution network having optical splitters. The PIC includes an array of optoelectronic circuitry sections, each receiving an optical wave from one of the output ports of the optical copying distribution network, and each optoelectronic circuitry section includes: at least one photodetector detecting at least one optical wave from the optoelectronic operation. The EIC includes electrical input ports receiving respective electrical values. The first semiconductor die and the second semiconductor die are electrically coupled in a controlled collapse chip connection, with the electrical output port of the PIC connected to one of the electrical input ports of the EIC. | 2021-07-01 |
20210201127 | HARDWARE STRUCTURE AWARE ADAPTIVE LEARNING BASED POWER MODELING METHOD AND SYSTEM - An adaptive learning power modeling method includes: sampling at least one of a plurality of network components to form a power consumption evaluation network according to at least one parameter within a parameter range; evaluating a predictive power consumption of a to-be-measured circuit by the power consumption evaluation network; training and evaluating an actual power consumption and the predictive power consumption of the to-be-measured circuit by the power consumption evaluation network to obtain an evaluation result; and performing training according to the evaluation result to determine whether to change the power consumption evaluation network. | 2021-07-01 |
20210201128 | SYSTEM AND METHOD FOR GENERATING SCORES FOR PREDICTING PROBABILITIES OF TASK COMPLETION - According to various embodiments, described herein are systems and methods for training machine learning (ML) models to generate real-time scores to predict the probabilities of task completion. In one embodiment, an exemplary method includes the operations of receiving, from a data store, a set of features and a workflow for training a first type of ML models, the workflow specifying a data source, a number of stages and associated parameters for training the ML models; retrieving, from the data source, training data for the set of features; and segmenting the training data into different segments. The method further includes the operations of training a separate first type of ML model using each of the different segment of the training data in accordance with the workflow; and persisting the first type of trained ML models into the data storage. The method also includes using a trained ML model to generate probability scores and displaying the scores to users in real-time. | 2021-07-01 |
20210201129 | COMBINING POINT OBSERVATIONS WITH RASTER DATA FOR MACHINE LEARNING - A computer produces predictions throughout a raster field in response to point data, by obtaining a partially empty matrix of point data, filling a matrix of extrapolated raster data by dilating the point data in a first convolutional neural network, and generating a matrix of aggregate raster data by combining the extrapolated raster data with organic raster data in a second convolutional neural network. | 2021-07-01 |
20210201130 | JOB-LAUNCH TIME REDUCTION BY NODE PRE-CONFIGURATION - Based on historic job data, a computer processor can predict a configuration of a computer node for running a future computer job. The computer processor can pre-configure the computer node based on the predicted configuration. Responsive to receiving a submission of a job, the computer processor can launch the job on the pre-configured computer node. | 2021-07-01 |
20210201131 | TRAINING ARTIFICIAL NEURAL NETWORKS BASED ON SYNAPTIC CONNECTIVITY GRAPHS - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a student neural network. In one aspect, there is provided a method comprising: processing a training input using the student neural network to generate a student neural network output comprising a respective score for each of a plurality of classes; processing the training input using a brain emulation neural network to generate a brain emulation neural network output comprising a respective score for each of the plurality of classes; and adjusting current values of the student neural network parameters using gradients of an objective function that characterizes a similarity between: (i) the student neural network output for the training input, and (ii) the brain emulation neural network output for the training input. | 2021-07-01 |
20210201132 | NEURAL NETWORK METHOD AND APPARATUS - A processor-implemented method of performing a convolution operation is provided. The method includes obtaining input feature map data and kernel data, determine the kernel data based on a number of input channels of the input feature map, a number of output channels of an output feature map, and a number of groups of the input feature map data and a number of groups of the kernel data related to the convolution operation, and performing the convolution operation based on the input feature map data and the determined kernel data. | 2021-07-01 |