Patents Examined by Kamran Afshar
  • Patent number: 11068772
    Abstract: Disclosed are methods, systems, and non-transitory computer-readable medium for executing neural network training for dynamically predicting apparel wearability. For example, a method may include generating a training data set comprising one or more historical data attributes of previously shipped apparel, training a neural network based on the training data set to configure one or more trained models to output a metric for any pair of a unique user identifier and a unique apparel identifier, storing one or more trained model objects, collecting prediction data comprising at least one prediction pair including a unique user identifier and a unique apparel identifier, predicting one or more predictive wearability metrics indicative of propensity to wear, dynamically generating one or more match pairs, and determining a match wearability metric for each of the one or more match pairs based on the predicted one or more predictive wearability metrics.
    Type: Grant
    Filed: February 14, 2019
    Date of Patent: July 20, 2021
    Assignee: CaaStle, Inc.
    Inventors: Li-Wei Chang, Dongming Jiang, Georgiy Goldenberg, Krishnan Vishwanath
  • Patent number: 11068777
    Abstract: Controllable resistance elements and methods of setting the same include a junction field effect transistor configured to provide a resistance on a signal line. A first pass transistor is configured to apply a charge increment or decrement to the junction field effect transistor responsive to a control pulse, such that the resistance on the signal line changes.
    Type: Grant
    Filed: February 6, 2017
    Date of Patent: July 20, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Stephen W. Bedell, Martin M. Frank, Devendra K. Sadana
  • Patent number: 11068780
    Abstract: Technologies for artificial neural network training include a computing node with a host fabric interface that sends a message that includes one or more artificial neural network training algorithm values to another computing node in response to receipt of a request to send the message. Prior to sending the message, the host fabric interface may receive a request to quantize the message and quantize the message based on a quantization level included in the request to generate a quantized message. The quantization message includes one or more quantized values such that each quantized value has a lower precision than a corresponding artificial neural network training algorithm value. The host fabric interface then transmits the quantized message, which includes metadata indicative of the quantization level, to another computing node in response to quantization of the message for artificial neural network training. Other embodiments are described and claimed.
    Type: Grant
    Filed: April 1, 2017
    Date of Patent: July 20, 2021
    Assignee: Intel Corporation
    Inventors: Naveen K. Mellempudi, Srinivas Sridharan, Dheevatsa Mudigere, Dipankar Das
  • Patent number: 11068790
    Abstract: Techniques are provided for imputation in computer-based reasoning systems. The techniques include performing the following until there are no more cases in a computer-based reasoning model with missing fields for which imputation is desired: determining which cases have fields to impute (e.g., missing fields) in the computer-based reasoning model and determining conviction scores and/or imputation order information for the cases that have fields to impute. The techniques proceed by determining for which cases to impute data and, for each of the determined one or more cases with missing fields to impute data is imputed for the missing field, and the case is modified with the imputed data. Control of a system is then caused using the updated computer-based reasoning model.
    Type: Grant
    Filed: January 27, 2020
    Date of Patent: July 20, 2021
    Assignee: Diveplane Corporation
    Inventors: Michael Resnick, Christopher James Hazard
  • Patent number: 11068802
    Abstract: The present disclosure is directed to a high-capacity training and prediction machine learning platform that can support high-capacity parameter models (e.g., with 10 billion parameters). The platform generates a model for a metric of interest based on a known training set. The model includes parameters indicating importances of different features of the model, taken both singly and in pairs. The model may be applied to predict a value for the metric for given sets of objects, such as for a pair consisting of a user object and a content item object.
    Type: Grant
    Filed: June 29, 2017
    Date of Patent: July 20, 2021
    Assignee: Facebook, Inc.
    Inventors: Andrey Malevich, Ou Jin
  • Patent number: 11062222
    Abstract: Mechanisms are provided for performing cross-user dashboard behavior analysis and dashboard recommendation generation. Dashboard interfaces are presented to a user and the user inputs are tracked. Cognitive analysis of the user dashboard behavior pattern data is performed to determine a reason for user dashboard behavior represented by the user dashboard behavior pattern data. Cross-user correlation analysis operations are performed based on the user dashboard behavior pattern data and dashboard behavior pattern data of other users of a different user type to identify an intersection point. A recommendation output is generated and output that recommends at least one of a particular dashboard interface to access or a modification to the one or more dashboard interfaces to be performed. The recommendation is based on the identification of the intersection point and the determined reason for the user dashboard behavior.
    Type: Grant
    Filed: September 6, 2017
    Date of Patent: July 13, 2021
    Assignee: International Business Machines Corporation
    Inventor: Kimberly S. Dunwoody
  • Patent number: 11062197
    Abstract: A neuromorphic computing system includes a synapse array, a switching circuit, a sensing circuit and a processing circuit. The synapse array includes row lines, column lines and synapses. The processing circuit is coupled to the switching circuit and the sensing circuit and is configured to connect a particular column line in the column lines to the first terminal by using the switching circuit, obtain a first voltage value from the particular column line by using the sensing circuit when the particular line is connected to the first terminal, connect the particular column line to the second terminal by using the switching circuit, obtain a second voltage value from the particular column line by using the sensing circuit when the particular line is connected to the second terminal, and estimate a sum-of-product sensing value according to a voltage difference between the first voltage value and the second voltage value.
    Type: Grant
    Filed: November 6, 2017
    Date of Patent: July 13, 2021
    Assignee: MACRONIX INTERNATIONAL CO., LTD.
    Inventors: Yu-Yu Lin, Feng-Min Lee
  • Patent number: 11062204
    Abstract: Methods of training a neural network include applying an input signal to an array of weights to generate weighted output signals based on resistances of respective weights in the array of weights. A difference between the weighted output signals and a predetermined expected output is determined. Weights in the array of weights are set by applying a pulse to a controllable resistance element in each weight. The pulse increments or decrements a charge on a junction field effect transistor in the respective controllable resistance element.
    Type: Grant
    Filed: November 3, 2017
    Date of Patent: July 13, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Stephen W. Bedell, Martin M. Frank, Devendra K. Sadana
  • Patent number: 11055628
    Abstract: A learning model difference providing method that causes a computer to execute a process which includes: calculating a mismatch degree between prediction data about arbitrary data included in a plurality of pieces of data that are input by using an application program, the prediction data being obtained by the plurality of pieces of data and a learning model in accordance with a purpose of use of the application program, and data that are specified for the arbitrary data; assessing whether or not the calculated mismatch degree exceeds a first degree; and transmitting the mismatch degree to a providing source of the learning model in a case where the mismatch degree is assessed as exceeding the first degree.
    Type: Grant
    Filed: April 27, 2017
    Date of Patent: July 6, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Tomo Kaniwa, Mitsuru Sato
  • Patent number: 11055616
    Abstract: An architecture for an explainable neural network may implement a number of layers to produce an output. The input layer may be processed by both a conditional network and a prediction network. The conditional network may include a conditional layer, an aggregation layer, and a switch output layer. The prediction network may include a feature generation and transformation layer, a fit layer, and a value output layer. The results of the switch output layer and value output layer may be combined to produce the final output layer. A number of different possible activation functions may be applied to the final output layer depending on the application. The explainable neural network may be implementable using both general purpose computing hardware and also application specific circuitry including optimized hardware only implementations. Various embodiments of XNNs are described that extend the functionality to different application areas and industries.
    Type: Grant
    Filed: November 17, 2020
    Date of Patent: July 6, 2021
    Assignee: UMNAI Limited
    Inventors: Angelo Dalli, Mauro Pirrone
  • Patent number: 11055612
    Abstract: Neural networks include neuron layers arranged in order from an input neuron layer to an output neuron layer, with at least one hidden layer between them. Weight arrays between respective pairs of neuron layers each include controllable resistance elements and AND gates configured to control addressing of the plurality of controllable resistance elements. Each controllable resistance element includes a junction field effect transistor configured to provide a resistance on a signal line and a first pass transistor configured to apply a charge increment or decrement to the junction field effect transistor responsive to a control pulse, such that the resistance on the signal line changes. The control pulse is only passed to a controllable resistance element when a respective AND gate is triggered. A training module is configured to train the neural network by adjusting resistances of the plurality of controllable resistance elements in each of the weight arrays.
    Type: Grant
    Filed: December 26, 2018
    Date of Patent: July 6, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Stephen W. Bedell, Martin M. Frank, Devendra K. Sadana
  • Patent number: 11055617
    Abstract: A device, system, and method for training or prediction of a neural network. A current value may be stored for each of a plurality of synapses or filters in the neural network. A historical metric of activity may be independently determined for each individual or group of the synapses or filters during one or more past iterations. A plurality of partial activations of the neural network may be iteratively executed. Each partial-activation iteration may activate a subset of the plurality of synapses or filters in the neural network. Each individual or group of synapses or filters may be activated in a portion of a total number of iterations proportional to the historical metric of activity independently determined for that individual or group of synapses or filters. Training or prediction of the neural network may be performed based on the plurality of partial activations of the neural network.
    Type: Grant
    Filed: June 30, 2020
    Date of Patent: July 6, 2021
    Assignee: DEEPCUBE LTD.
    Inventors: Eli David, Eri Rubin
  • Patent number: 11049039
    Abstract: Disclosed herein are cloud-based machine learning systems and methods for monitoring networked devices to identify and classify characteristics, to infer typical or atypical behavior and assign reputation profiles across various networked devices, and to make remediation recommendations. In some embodiments, a cloud-based machine learning system may learn the typical operation and interfacing of a plurality of reputable devices that are known to be free from malicious software and other threats. In some embodiments, a cloud-based machine learning system may learn the typical operation and interfacing of a device, and may identify atypical operations or interfaces associated with that device by comparing the operations and interfaces to those of a plurality of networked devices or to those of a defined standard reference device.
    Type: Grant
    Filed: September 30, 2016
    Date of Patent: June 29, 2021
    Assignee: McAfee, LLC
    Inventors: Vincent J. Zimmer, Joel R. Spurlock, Ramnath Venugopalan, Ned M. Smith, Igor G. Muttik, Rajesh Poornachandran
  • Patent number: 11049004
    Abstract: Detection systems, methods and computer program products comprising a non-transitory tangible storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method for anomaly detection, a detected anomaly being indicative of an undesirable event. A detection system comprises a computer and an anomaly detection engine executable by the computer, the anomaly detection engine configured to perform a method comprising receiving data comprising a plurality m of multidimensional data points (MDDPs), each data point having n features, constructing a dictionary D based on the received data, embedding dictionary D into a lower dimension embedded space and classifying, based in the lower dimension embedded space, a MDDP as an anomaly or as normal.
    Type: Grant
    Filed: November 11, 2016
    Date of Patent: June 29, 2021
    Assignee: ThetaRay Ltd.
    Inventor: David Segev
  • Patent number: 11049031
    Abstract: A disclosed example method to predict an injury for a target player on a target date includes determining a first probability of injury of the target player based on probabilities of injuries of second players having similarities with the target player; determining a second probability of injury of the target player based on injuries of the target player; determining a third probability of injury of the target player based on the first probability of injury of the target player and the second probability of injury of the target player; and generating, by executing an instruction with the processor, a report of a predicted probability of injury of the target player for the target date based on the third probability of injury of the target player.
    Type: Grant
    Filed: March 31, 2017
    Date of Patent: June 29, 2021
    Assignee: Intel Corporation
    Inventors: Rita Chattopadhyay, Kalpana A. Algotar, Ali Ashrafi, John Pilkin
  • Patent number: 11049001
    Abstract: The present invention provides a system comprising multiple core circuits. Each core circuit comprises multiple electronic axons for receiving event packets, multiple electronic neurons for generating event packets, and a fanout crossbar including multiple electronic synapse devices for interconnecting the neurons with the axons. The system further comprises a routing system for routing event packets between the core circuits. The routing system virtually connects each neuron with one or more programmable target axons for the neuron by routing each event packet generated by the neuron to the target axons. Each target axon for each neuron of each core circuit is an axon located on the same core circuit as, or a different core circuit than, the neuron.
    Type: Grant
    Filed: July 30, 2018
    Date of Patent: June 29, 2021
    Assignee: International Business Machines Corporation
    Inventors: Rodrigo Alvarez-Icaza Rivera, John V. Arthur, Andrew S. Cassidy, Bryan L. Jackson, Paul A. Merolla, Dharmendra S. Modha, Jun Sawada
  • Patent number: 11048707
    Abstract: Aspects of the present disclosure relate to identifying a product in a document. A server accesses a document including scientific or research-related text. The server divides the document into a plurality of tokens, each token comprising a part of the text that logically comprises a unit of information. The server computes, for each token in the plurality of tokens, a score corresponding to whether the token corresponds to a commercial product, the score being computed based on a list of features of commercial products and weights assigned to features in the list. The server determines that the score exceeds a threshold score. The server provides, in response to determining that the score exceeds the threshold score, an output representing that the token corresponds to the commercial product.
    Type: Grant
    Filed: June 28, 2017
    Date of Patent: June 29, 2021
    Assignee: ResearchGate GmbH
    Inventors: Viacheslav Zholudev, Darren Alvares, Niall Kelly, Tilo Mathes, Axel Tölke, Vincenz Priesnitz, Thoralf Klein
  • Patent number: 11049021
    Abstract: Aspects of the present disclosure involve systems, methods, devices, and the like for generating compact tree representations applicable to machine learning. In one embodiment, a system is introduced that can retrieve a decision tree structure to generate a compact tree representation model. The compact tree representation model may come in the form of a matrix design to maintain the relationships expressed by the decision tree structure.
    Type: Grant
    Filed: October 5, 2017
    Date of Patent: June 29, 2021
    Assignee: PayPal, Inc.
    Inventors: Raoul Christopher Johnson, Omri Moshe Lahav, Michael Dymshits, David Tolpin
  • Patent number: 11049006
    Abstract: Techniques and constructs can reduce the time required to determine solutions to optimization problems such as training of neural networks. Modifications to a computational model can be determined by a plurality of nodes operating in parallel. Quantized modification values can be transmitted between the nodes to reduce the volume of data to be transferred. The quantized values can be as small as one bit each. Quantization-error values can be stored and used in quantizing subsequent modifications. The nodes can operate in parallel and overlap computation and data transfer to further reduce the time required to determine solutions. The quantized values can be partitioned and each node can aggregate values for a corresponding partition.
    Type: Grant
    Filed: September 12, 2014
    Date of Patent: June 29, 2021
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: John Langford, Gang Li, Frank Torsten Bernd Seide, James Droppo, Dong Yu
  • Patent number: 11042814
    Abstract: A computer system can perform a semi-supervised machine learning processes to cluster a plurality of entities within a population based on their features and associated labels. The computer system can generate visualization data representing the clusters of entities and associated labels for displaying on a user interface. A user can review the clustering of entities and use the user interface to add or modify the labels associated with a particular entity or set of entities. The computer system can use the user's feedback to update the labels and then re-determine the clustering of entities using the semi-supervised machine learning process with the updated labels as input. As such, the computer system can use the user's feedback to improve the accuracy of the machine learning model without requiring a larger amount of labeled input data.
    Type: Grant
    Filed: March 17, 2017
    Date of Patent: June 22, 2021
    Assignee: Visa International Service Association
    Inventors: Liang Gou, Hao Yang