Patents Examined by Fayyaz Alam
  • Patent number: 11556855
    Abstract: A machine learning model including an autoencoder may be trained based on training data that includes sequences of non-anomalous performance metrics from an information technology system but excludes sequences of anomalous performance metrics. The trained machine learning model may process a sequence of performance metrics from the information technology system by generating an encoded representation of the sequence of performance metrics and generating, based on the encoded representation, a reconstruction of the sequence of performance metrics. An occurrence of the anomaly at the information technology system may be detected based on a reconstruction error present in reconstruction of the sequence of performance metrics. Related systems, methods, and articles of manufacture are provided.
    Type: Grant
    Filed: May 22, 2020
    Date of Patent: January 17, 2023
    Assignee: SAP SE
    Inventors: Rajendra Kumar, Rahul Choudhary, Seshadri Chatterjee
  • Patent number: 11551028
    Abstract: A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights. A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism.
    Type: Grant
    Filed: May 21, 2020
    Date of Patent: January 10, 2023
    Inventors: Avi Baum, Or Danon, Daniel Chibotero, Gilad Nahor
  • Patent number: 11553413
    Abstract: Briefly, in accordance with one or more embodiments, a user equipment (UE) may enter into an E-UTRAN Routing Area Paging Channel state, and is configured with an E-UTRAN Routing Area and an Anchor identifier to identify an anchor evolved Node B (eNB) for the UE. The UE selects to a new cell without performing a handover procedure, and performs a cell update procedure. The UE also may enter into a Cell Update Connected state, and is configured with an Anchor identifier. The UE selects to a new cell, performs a cell update procedure, performs a buffer request procedure, and performs a cell update procedure to download buffered data and to perform data transmission with the new cell.
    Type: Grant
    Filed: June 25, 2020
    Date of Patent: January 10, 2023
    Assignee: Apple Inc.
    Inventors: Alexandre S. Stojanovski, Ana Lucia A. Pinheiro, Richard C. Burbidge, Candy Yiu, Youn Hyoung Heo, Sangeetha L. Bangolae
  • Patent number: 11551039
    Abstract: Neural network-based categorization can be improved by incorporating graph neural networks that operate on a graph representing the taxonomy of the categories into which a given input is to be categorized by the neural network based-categorization. The output of a graph neural network, operating on a graph representing the taxonomy of categories, can be combined with the output of a neural network operating upon the input to be categorized, such as through an interaction of multidimensional output data, such as a dot product of output vectors. In such a manner, information conveying the explicit relationships between categories, as defined by the taxonomy, can be incorporated into the categorization. To recapture information, incorporate new information, or reemphasize information a second neural network can also operate upon the input to be categorized, with the output of such a second neural network being merged with the output of the interaction.
    Type: Grant
    Filed: April 28, 2020
    Date of Patent: January 10, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Tianchuan Du, Keng-hao Chang, Ruofei Zhang, Paul Liu
  • Patent number: 11538253
    Abstract: An apparatus and method for compensating for an error of a vehicle sensor for enhancing performance for identifying the same object are provided. The apparatus includes a rotation angle error calculator that calculates a rotation angle error between sensor object information and sensor fusion object information. A position error calculator calculates a longitudinal and lateral position error between the sensor object information and the sensor fusion object information. A sensor error compensator calculates a sensor error based on the calculated rotation angle and a position error. In calculating the rotation angle error, the sensor error compensator corrects an error of the sensor object information based on the rotation angle error, and compensates for the sensor error based on the longitudinal and lateral position error between the corrected sensor object information and the sensor fusion object information.
    Type: Grant
    Filed: March 30, 2020
    Date of Patent: December 27, 2022
    Assignees: Hyundai Motor Company, Kia Motors Corporation
    Inventor: Wooyoung Lee
  • Patent number: 11531710
    Abstract: A method and system of graph feature extraction and graph classification based on adjacency matrix is provided. The invention first concentrates the connection information elements in the adjacency matrix into a specific diagonal region of the adjacency matrix which reduces the non-connection information elements in advance. Then the subgraph structure of the graph is further extracted along the diagonal direction using the filter matrix. Further, it uses a stacked convolutional neural network to extract a larger subgraph structure. On one hand, it greatly reduces the amount of computation and complexity, getting rid of the limitations caused by computational complexity and window size. On the other hand, it can capture large subgraph structure through a small window, as well as deep features from the implicit correlation structures at both vertex and edge level, which improves speed and accuracy of graph classification.
    Type: Grant
    Filed: November 26, 2019
    Date of Patent: December 20, 2022
    Assignee: ZHEJIANG UNIVERSITY
    Inventors: Jianwei Yin, Zhiling Luo, Zhaohui Wu, Shuiguang Deng, Ying Li, Jian Wu
  • Patent number: 11531886
    Abstract: Method and system for predicting labels for nodes in an observed graph, including deriving a plurality of random graph realizations of the observed graph; learning a predictive function using the random graph realizations; predicting label probabilities for nodes of the random graph realizations using the learned predictive function; and averaging the predicted label probabilities to predict labels for the nodes of the observed graph.
    Type: Grant
    Filed: November 26, 2019
    Date of Patent: December 20, 2022
    Assignees: THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING/MCGILL UNIVERSITY, HUAWEI TECHNOLOGIES CANADA CO., LTD.
    Inventors: Yingxue Zhang, Soumyasundar Pal, Mark Coates, Deniz Ustebay
  • Patent number: 11514252
    Abstract: A discriminative captioning system generates captions for digital images that can be used to tell two digital images apart. The discriminative captioning system includes a machine learning system that is trained by a discriminative captioning training system that includes a retrieval machine learning system. For training, a digital image is input to the caption generation machine learning system, which generates a caption for the digital image. The digital image and the generated caption, as well as a set of additional images, are input to the retrieval machine learning system. The retrieval machine learning system generates a discriminability loss that indicates how well the retrieval machine learning system is able to use the caption to discriminate between the digital image and each image in the set of additional digital images. This discriminability loss is used to train the caption generation machine learning system.
    Type: Grant
    Filed: June 10, 2018
    Date of Patent: November 29, 2022
    Assignee: Adobe Inc.
    Inventors: Brian Lynn Price, Ruotian Luo, Scott David Cohen
  • Patent number: 11514270
    Abstract: Embodiments may include a method to estimate motion data based on test image data sets. The method may include receiving a training data set comprising a plurality of training data elements. Each element may include an image data set and a motion data set. The method may include training a machine learning model using the training data set, resulting in identifying one or more parameters of a function in the machine learning model based on correspondences between the image data sets and the motion data sets. The method may further include receiving a test image data set. The test image data set may include intensities of pixels in a deep-tissue image. The method may include using the trained machine learning model and the test image data set to generate output data for the test image data set. The output data may characterize motion represented in the test image data set.
    Type: Grant
    Filed: July 27, 2020
    Date of Patent: November 29, 2022
    Assignee: VERILY LIFE SCIENCES LLC
    Inventors: Eden Rephaeli, Daniele Piponi, Chinmay Belthangady, Seung Ah Lee
  • Patent number: 11514323
    Abstract: A method for training a homography attention module (HAM) to perform multi-view object detection includes steps of: generating, from an i-th feature map corresponding to each of multiple training images representing multi-views of a target space, a 1-st to a d-th channel attention map for determining channel attention scores each channel included in the i-th feature map has for each of a 1-st to a d-th height plane of the target space, generating a 1-st to a d-th channel refined feature map by referring to channels with top k channel attention scores for each height, element-wisely multiplying them with corresponding spatial attention map generated therefrom to produce a 1-st to a d-th spatial refined feature map, and then homographically transforming them onto corresponding height plane and aggregating them to generate a BEV occupancy heatmap, which is used with its GT for training.
    Type: Grant
    Filed: June 10, 2022
    Date of Patent: November 29, 2022
    Assignee: DEEPING SOURCE INC.
    Inventor: Jin Woo Hwang
  • Patent number: 11507753
    Abstract: Provided are processes of balancing between exploration and optimization with knowledge discovery processes applied to unstructured data with tight interrogation budgets. A process may determine an alignment score of each entity participating in an evaluation of a feature in a knowledge discovery process based on feedback received from the respective entities for the feature. Feedback of an entity that is mapped in the PGN may be processed to determine an alignment score of the entity for the feature, e.g., based on how the entity scored a feature. A plurality of different distributions indicative of alignment scores may be processed for display to visually indicate to a user the alignment of participating entities in their evaluations of the features.
    Type: Grant
    Filed: October 1, 2021
    Date of Patent: November 22, 2022
    Assignee: CrowdSmart, Inc.
    Inventors: Thomas Kehler, Markus Guehrs, Sonali Sinha
  • Patent number: 11501470
    Abstract: Disclosed in some examples are methods, systems, devices, and machine-readable mediums which encode data into a geometric representation for more efficient and secure processing. For example, data may be converted from a binary representation to a geometric representation using an encoding dictionary. The encoding dictionary specifies one or more geometric shapes used in the encoding. The geometrically encoded data may comprise one or more identifiers that specify one or more of the shapes of the encoding dictionary that best match one or more detected features in an image corresponding to the data. In some examples, the geometrically encoded data may also comprise one or more transformations of the one or more shapes to reduce error in the geometric encoding.
    Type: Grant
    Filed: May 27, 2020
    Date of Patent: November 15, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Amer Aref Hassan, Edward C. Giaimo, III
  • Patent number: 11494639
    Abstract: Performing an adversarial attack on a neural network classifier is described. A dataset of input-output pairs is constructed, each input element of the input-output pairs randomly chosen from a search space, each output element of the input-output pairs indicating a prediction output of the neural network classifier for the corresponding input element. A Gaussian process is utilized on the dataset of input-output pairs to optimize an acquisition function to find a best perturbation input element from the dataset. The best perturbation input element is upsampled to generate an upsampled best input element. The upsampled best input element is added to an original input to generate a candidate input. The neural network classifier is queried to determine a classifier prediction for the candidate input. A score for the classifier prediction is computed. The candidate input is accepted as a successful adversarial attack responsive to the classifier prediction being incorrect.
    Type: Grant
    Filed: September 24, 2019
    Date of Patent: November 8, 2022
    Assignee: Robert Bosch GmbH
    Inventors: Satya Narayan Shukla, Anit Kumar Sahu, Devin Willmott, Jeremy Zieg Kolter
  • Patent number: 11475299
    Abstract: A side information calculating unit (110) calculates side information for assisting either identification processing or classification processing. When there is a discrepancy between a processing result of either the identification processing or the classification processing, and the side information, the multilayer neural network (120) changes an output value of an intermediate layer (20) and performs either the identification processing or the classification processing again.
    Type: Grant
    Filed: August 10, 2017
    Date of Patent: October 18, 2022
    Assignee: MITSUBISHI ELECTRIC CORPORATION
    Inventor: Kenya Sugihara
  • Patent number: 11468667
    Abstract: Aspects of the present disclosure describe systems, methods and structures providing wide-area traffic monitoring based on distributed fiber-optic sensing (DFOS) that employs deep neural network(s) for denoising noisy waterfall traces measured by the DFOS. Such systems, methods, and structures according to aspects of the present disclosure may advantageously monitor multiple highways/roadways using a single interrogator and optical fiber switch(es) which provides traffic information along every sensing point of existing, deployed, in-service optical telecommunications facilities.
    Type: Grant
    Filed: June 15, 2020
    Date of Patent: October 11, 2022
    Assignee: NEC Corporation
    Inventors: Milad Salemi, Ming-Fang Huang
  • Patent number: 11463602
    Abstract: An image processing method includes an acquisition step of acquiring image data by capturing printed matter, wherein first information and second information, indicating a type of the first information, are embedded in the printed matter as an electronic watermark, an extraction step of extracting the first information and the second information from the image data acquired at the acquisition step, and a processing step of processing the extracted first information by different processing methods in accordance with the extracted second information. Based on that the type of the first information indicated by the second information is a predetermined type, the extracted first information is processed at the processing step, by a predetermined processing method for access to an external device using the extracted first information and display of a web page based on the access.
    Type: Grant
    Filed: July 16, 2020
    Date of Patent: October 4, 2022
    Assignee: Canon Kabushiki Kaisha
    Inventor: Ryoya Kawai
  • Patent number: 11462003
    Abstract: A system with a multiplication circuit having a plurality of multipliers is disclosed. Each of the plurality of multipliers is configured to receive a data value and a weight value to generate a product value in a convolution operation of a machine learning application. The system also includes an accumulator configured to receive the product value from each of the plurality of multipliers and a register bank configured to store an output of the convolution operation. The accumulator is further configured to receive a portion of values stored in the register bank and combine the received portion of values with the product values to generate combined values. The register bank is further configured to replace the portion of values with the combined values.
    Type: Grant
    Filed: March 25, 2020
    Date of Patent: October 4, 2022
    Assignee: Western Digital Technologies, Inc.
    Inventors: Kiran Gunnam, Anand Kulkarni, Zvonimir Bandic
  • Patent number: 11461619
    Abstract: Systems and methods for implementing a spatial and temporal attention-based gated recurrent unit (GRU) for node classification over temporal attributed graphs are provided. The method includes computing, using a GRU, embeddings of nodes at different snapshots. The method includes performing weighted sum pooling of neighborhood nodes for each node. The method further includes concatenating feature vectors for each node. Final temporal network embedding vectors are generated based on the feature vectors for each node. The method also includes applying a classification model based on the final temporal network embedding vectors to the plurality of nodes to determine temporal attributed graphs with classified nodes.
    Type: Grant
    Filed: February 11, 2020
    Date of Patent: October 4, 2022
    Inventors: Wei Cheng, Haifeng Chen, Dongkuan Xu
  • Patent number: 11455501
    Abstract: Examples disclosed herein relate to determining a response based on hierarchical models. In one implementation, a processor applies a first model to an image of an environment to select a second model. The processor applies the selected second model to the image and creates an environmental description representation based on the output of the second model. The processor determines a response based on the environmental description information.
    Type: Grant
    Filed: February 21, 2018
    Date of Patent: September 27, 2022
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Thomas Paula, Carlos Leao
  • Patent number: 11455540
    Abstract: An autonomic function is caused to execute in an artificial intelligence environment to detect a new problem space. Using the autonomic function, a first model is selected. The first model includes a first trained neural network corresponding to a first ontology. A second model is automatically identified. the second model includes a second trained neural network corresponding to a second ontology. A layer is autonomically extracted from the second model and inserted into a location in the first model. A vector transformation is automatically constructed to transform an output vector of a previous layer in an immediately previous location in the model relative to the location. The layer is automatically fused in the first model using the transformed output vector as input to the layer, the fusing forming a fused model that is operable on an ontology of the new problem space.
    Type: Grant
    Filed: November 15, 2019
    Date of Patent: September 27, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Aaron K. Baughman, Michael Behrendt, Shikhar Kwatra, Craig M. Trim