Patents Examined by Benjamin P. Geib
  • Patent number: 11562246
    Abstract: Methods and computer systems improve a trained base deep neural network by structurally changing the base deep neural network to create an updated deep neural network, such that the updated deep neural network has no degradation in performance relative to the base deep neural network on the training data. The updated deep neural network is subsequently training. Also, an asynchronous agent for use in a machine learning system comprises a second machine learning system ML2 that is to be trained to perform some machine learning task. The asynchronous agent further comprises a learning coach LC and an optional data selector machine learning system DS. The purpose of the data selection machine learning system DS is to make the second stage machine learning system ML2 more efficient in its learning (by selecting a set of training data that is smaller but sufficient) and/or more effective (by selecting a set of training data that is focused on an important task).
    Type: Grant
    Filed: May 25, 2022
    Date of Patent: January 24, 2023
    Assignee: D5AI LLC
    Inventor: James K. Baker
  • Patent number: 11556764
    Abstract: Systems and methods for deriving a concordant software neural network layer are provided. A method includes receiving first instructions configured to, using a neural network processor (NNP), process a first set of data corresponding to a neural network layer, where the NNP is configured to quantize the first set of the data to generate a set of quantized data and then perform matrix-vector multiply operations on the set of quantized data using a matrix-vector-multiplier incorporated within hardware associated with the NNP to generate a first set of results. The method further includes processing the first instructions to automatically generate second instructions configured for use with at least one processor, different from the NNP, such that the second instructions, when executed by the at least one processor to perform matrix multiply operations, generate a second set of results that are concordant with the first set of results.
    Type: Grant
    Filed: March 1, 2019
    Date of Patent: January 17, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jeremy Fowers, Daniel Lo, Deeksha Dangwal
  • Patent number: 11556762
    Abstract: Neural network processors that have been customized based on application specific synthesis specialization parameters and related methods are described. Certain example neural network processors and methods described in the present disclosure expose several major synthesis specialization parameters that can be used for specializing a microarchitecture instance of a neural network processor to specific neural network models including: (1) aligning the native vector dimension to the parameters of the model to minimize padding and waste during model evaluation, (2) increasing lane widths to drive up intra-row-level parallelism, or (3) increasing matrix multiply tiles to exploit sub-matrix parallelism for large neural network models.
    Type: Grant
    Filed: April 21, 2018
    Date of Patent: January 17, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jeremy Fowers, Kalin Ovtcharov, Eric S. Chung, Todd Michael Massengill, Ming Gang Liu, Gabriel Leonard Weisz
  • Patent number: 11544552
    Abstract: A method, apparatus and computer program product refine an automated coding model, such as for a medical chart. For each respective candidate code from a set of candidate codes, the method predicts a probability of the respective code being contained in a medical chart. The method also selects one of the candidate codes as being contained in the medical chart based upon the probability and removes the selected candidate code from the set of candidate codes. The method then repeatedly predicts the probability of a respective code being contained in the medical chart, selects one of the candidate codes based upon the predicted probability and removes the selected candidate code from the set of candidate codes. The method further determines a categorical crossentropy loss as to permit adjustment of one or more parameters of the automated coding model.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: January 3, 2023
    Assignee: CHANGE HEALTHCARE HOLDINGS, LLC
    Inventors: Alex Londeree, Nick Giannasi, Adrian Lam, Adam Sullivan
  • Patent number: 11544582
    Abstract: Embodiments of the present invention disclose system to determine the best model to perform lead scoring for a given data set. The system can perform a multi-step iterative procedure including variable selection, feature set selection, training data selection, model development, model validation and process optimization. The system also performs local and global optimizations iteratively to determine the best possible model for a given scenario.
    Type: Grant
    Filed: February 2, 2017
    Date of Patent: January 3, 2023
    Assignee: Ambertag, Inc.
    Inventors: Kanchana Suryakantha, Kashyap Subramanya, Vasanti Hegde, Rajaram Venkatesha Rao Kudli
  • Patent number: 11544606
    Abstract: Systems and methods for compressing target content are disclosed. In one embodiment, a system may include non-transient electronic storage and one or more physical computer processors. The one or more physical computer processors may be configured by machine-readable instructions to obtain the target content comprising one or more frames, wherein a given frame comprises one or more features. The one or more physical computer processors may be configured by machine-readable instructions to obtain a conditioned network. The one or more physical computer processors may be configured by machine-readable instructions to generate decoded target content by applying the conditioned network to the target content.
    Type: Grant
    Filed: January 22, 2019
    Date of Patent: January 3, 2023
    Assignee: Disney Enterprises, Inc.
    Inventors: Stephan Marcel Mandt, Christopher Schoers, Jun Han, Salvator D. Lombardo
  • Patent number: 11531877
    Abstract: A method of deploying a neural network on a target device method includes extracting a number of device dependent error masks from the target device, using the number of device dependent error masks in a training phase of the neural network to generate a device dependent weight matrix for the neural network, and storing the device dependent weight matrix in the target device for use by the target device to perform inference tasks using the neural network.
    Type: Grant
    Filed: October 19, 2018
    Date of Patent: December 20, 2022
    Assignees: University of Pittsburgh—Of The Commonwealth System of Higher Education, Hefei University of Technology
    Inventors: Youtao Zhang, Lei Zhao, Jun Yang, Shuai Ding
  • Patent number: 11530139
    Abstract: A cooperative fuzzy-neural control method is designed in this present invention. Due to the difficulty for cooperatively controlling the concentrations of the dissolved oxygen and nitrate nitrogen in wastewater treatment process, a cooperative fuzzy-neural control method is investigated. In this proposed method, firstly, a interval type-2 fuzzy neural network is employed to construct the cooperative fuzzy-neural controller. Secondly, a parameter cooperative strategy is proposed to cooperatively optimize the global and local parameters of the cooperative fuzzy-neural controller to meet the control requirements. This proposed cooperative fuzzy-neural control method can cooperatively control the concentrations of the dissolved oxygen and nitrate nitrogen in wastewater treatment process. The results illustrate that the proposed cooperative fuzzy-neural control method can achieve the high control accuracy and guarantee the normal operations of wastewater treatment process under the different operation conditions.
    Type: Grant
    Filed: November 25, 2019
    Date of Patent: December 20, 2022
    Assignee: BEIJING UNIVERSITY OF TECHNOLOGY
    Inventors: Honggui Han, Jiaming Li, Xiaolong Wu, Junfei Qiao
  • Patent number: 11531876
    Abstract: Systems and methods for a computer-based visual recognition based upon a spatially forked deep learning architecture, including unification of deep learning and reasoning. A method can include a primary learner with an adjacent structured memory bank that can not only predict the output from a given input, but also relate the input to all past memorized instances and help in creative understanding.
    Type: Grant
    Filed: March 29, 2018
    Date of Patent: December 20, 2022
    Assignee: UNIVERSITY OF FLORIDA RESEARCH FOUNDATION, INCORPORATED
    Inventors: Dapeng Oliver Wu, Pratik Brahma
  • Patent number: 11531934
    Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: identifying a training data set and defining a window for an initial beta value representing bias tolerated in formulating expectation conditional to each feature vector from the training data set. The conditional expectations are parallelly regularized by use of DNA computer. Amongst numerous combinations of candidate models, a best fit ensemble is produced as the machine learning model for predicting targeted outcomes based on inputs other than the training data set.
    Type: Grant
    Filed: May 31, 2018
    Date of Patent: December 20, 2022
    Assignee: Kyndryl, Inc.
    Inventors: Gary F. Diamanti, Aaron K. Baughman, Mauro Marzorati
  • Patent number: 11526742
    Abstract: Method and system for intelligent decision-making photonic signal processing, where the system comprises a multi-functional input unit, an electro-optical conversion module, a signal processing module, a photoelectric conversion module, a multi-functional output unit, and an artificial intelligence chip. The invention combines the advantages of photonic high-speed, wide-band, and electronic flexibility, combined with heterogeneous photoelectron hybrid integration, packaging and other processes, along with deep learning algorithm, is an intelligent electronic information system that may simultaneously realize digital and analog signal processing.
    Type: Grant
    Filed: September 14, 2018
    Date of Patent: December 13, 2022
    Assignee: Shanghai Jiao Tong University
    Inventors: Weiwen Zou, Lei Yu, Shaofu Xu, Bowen Ma, Jianping Chen
  • Patent number: 11521101
    Abstract: In one aspect, a computer implemented method for translating and executing rules using a directed acyclic graph is provided. The method includes transforming a ruleset into a directed acyclic graph. The directed acyclic graph includes a plurality of nodes and a plurality of branches. The method further includes identifying similarities across the plurality of branches. The method further includes grouping branches of the directed acyclic graph based on the identified similarities. The method further includes creating a modified directed acyclic graph based on the grouping. The method further includes selecting and using a method of processing a group of the modified directed acyclic graph based on an aspect of the group.
    Type: Grant
    Filed: October 31, 2018
    Date of Patent: December 6, 2022
    Assignee: Fair Isaac Corporation
    Inventors: Jean-Luc M. Marcé, Gabrio Verratti, Rafay Abdur, Andrei R. Yershov, John Wearing
  • Patent number: 11514290
    Abstract: Disclosed is a convolutional neural network (CNN) processing apparatus and method, the apparatus configured to determine a loading space unit for at least one loading space in an input based on a height or a width for an input feature map of the input and an extent of a dimension of a kernel feature map, load target input elements corresponding to a target loading space, among the at least one loading space, from a memory and store the target input elements in an allocated input buffer having a size corresponding to the loading space unit, and perform a convolution operation between the target input elements stored in the input buffer and at least one kernel element of a kernel.
    Type: Grant
    Filed: December 11, 2017
    Date of Patent: November 29, 2022
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Jinwoo Son, Changyong Son, Jaejoon Han, Chang Kyu Choi
  • Patent number: 11501138
    Abstract: Some embodiments provide a neural network inference circuit (NNIC) for executing a neural network that includes multiple computation nodes at multiple layers. The NNIC includes a set of clusters of core computation circuits and a channel, connecting the core computation circuits, that includes separate segments corresponding to each of the clusters. The NNIC includes a fabric controller circuit, a cluster controller circuit for each of the clusters, and a core controller circuit for each of the core computation circuits. The fabric controller circuit receives high-level neural network instructions from a microprocessor and parses the high-level neural network instructions.
    Type: Grant
    Filed: December 6, 2018
    Date of Patent: November 15, 2022
    Assignee: PERCEIVE CORPORATION
    Inventors: Kenneth Duong, Jung Ko, Steven L. Teig
  • Patent number: 11487990
    Abstract: Cross-point arrays and methods of updating values of the same include input resistive processing units (RPUs), each having a settable resistance, each connected to a common node. Output RPUs each have a settable resistance and are each connected to the common node. An update switch is configured to connect an update voltage to the common node.
    Type: Grant
    Filed: June 14, 2019
    Date of Patent: November 1, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Seyoung Kim, Tayfun Gokmen
  • Patent number: 11476869
    Abstract: A deep neural network (DNN) module is disclosed that can dynamically partition neuron workload to reduce power consumption. The DNN module includes neurons and a group partitioner and scheduler unit. The group partitioner and scheduler unit divides a workload for the neurons into partitions in order to maximize the number of neurons that can simultaneously process the workload. The group partitioner and scheduler unit then assigns a group of neurons to each of the partitions. The groups of neurons in the DNN module process the workload in their assigned partition to generate a partial output value. The neurons in each group can then sum their partial output values to generate a final output value for the workload. The neurons can be powered down once the groups of neurons have completed processing their assigned workload to reduce power consumption.
    Type: Grant
    Filed: April 13, 2018
    Date of Patent: October 18, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Amol Ashok Ambardekar, Boris Bobrov, Chad Balling McBride, George Petre, Kent D. Cedola, Larry Marvin Wall
  • Patent number: 11475311
    Abstract: An artificial neural network is implemented via an instruction stream. A header of the instruction stream and a format for instructions in the instruction stream are defined. The format includes an opcode, an address, and data. The instruction stream is created using the header, the opcode, the address, and the data. The artificial neural network is implemented by providing the instruction stream to a computer processor for execution of the instruction stream.
    Type: Grant
    Filed: October 30, 2019
    Date of Patent: October 18, 2022
    Assignee: Raytheon Company
    Inventors: John E. Mixter, David R. Mucha
  • Patent number: 11468336
    Abstract: Embodiments relate to systems, devices, and computing-implemented methods for generating domain name suggestions by obtaining a domain name suggestion input that includes textual data, segmenting the textual data into tokens, obtaining a list of possible affixes to the textual data, determining conditional probabilities for the possible affixes using a language model, ranking the list of possible affixes based on the conditional probabilities to generate a ranked list of affixes, and generating domain name suggestions based on the ranked list of affixes.
    Type: Grant
    Filed: June 6, 2016
    Date of Patent: October 11, 2022
    Assignee: VeriSign, Inc.
    Inventors: Vincent Raemy, Aubry Cholleton
  • Patent number: 11454939
    Abstract: Techniques are provided herein for creating well-balanced computer-based reasoning systems and using those to control systems. The techniques include receiving a request to determine whether to include one or more particular data elements in a computer-based reasoning model and determining two probability density or mass functions (“PDMFs”), one for the data set including the one or more particular data elements, once for the data set excluding it. Surprisal is determined based on those two PDMFs, and inclusion in the computer-based reasoning model is determined based on surprisal. A system is later controlled using the computer-based reasoning model.
    Type: Grant
    Filed: April 9, 2018
    Date of Patent: September 27, 2022
    Assignee: Diveplane Corporation
    Inventor: Christopher James Hazard
  • Patent number: 11449046
    Abstract: A method includes obtaining operating data associated with operation of a cross-directional industrial process controlled by at least one model-based process controller. The method also includes, during a training period, performing closed-loop model identification with a first portion of the operating data to identify multiple sets of first spatial and temporal models. The method further includes identifying clusters associated with parameter values of the first spatial and temporal models. The method also includes, during a testing period, performing closed-loop model identification with a second portion of the operating data to identify second spatial and temporal models. The method further includes determining whether at least one parameter value of at least one of the second spatial and temporal models falls outside at least one of the clusters.
    Type: Grant
    Filed: June 1, 2017
    Date of Patent: September 20, 2022
    Assignee: Honeywell Limited
    Inventors: Qiugang Lu, R. Bhushan Gopaluni, Michael G. Forbes, Philip D. Loewen, Johan U. Backstrom, Guy A. Dumont