Patents Examined by Kakali Chaki
  • Patent number: 10152677
    Abstract: A mechanism is provided in a stream computing platform for data stream change detection and model swapping. The mechanism builds a model for each input data stream in a stream computing platform. Each tuple of each given input data stream is tagged with a key corresponding to the given input data stream. The mechanism performs an operation on each input data stream using its corresponding model. The mechanism detects a misdirected input data stream, which is tagged with a key that does not correspond to the misdirected input data stream. The mechanism pauses the misdirected input data stream swaps a model corresponding to the misdirected input data stream with another model corresponding to another paused input data stream.
    Type: Grant
    Filed: June 18, 2015
    Date of Patent: December 11, 2018
    Assignee: International Business Machines Corporation
    Inventors: Alain E. Biem, Dattaram Bijavara Aswathanarayana Rao, Bharath K. Devaraju
  • Patent number: 10147046
    Abstract: A mechanism is provided in a stream computing platform for data stream change detection and model swapping. The mechanism builds a model for each input data stream in a stream computing platform. Each tuple of each given input data stream is tagged with a key corresponding to the given input data stream. The mechanism performs an operation on each input data stream using its corresponding model. The mechanism detects a misdirected input data stream, which is tagged with a key that does not correspond to the misdirected input data stream. The mechanism pauses the misdirected input data stream swaps a model corresponding to the misdirected input data stream with another model corresponding to another paused input data stream.
    Type: Grant
    Filed: October 30, 2014
    Date of Patent: December 4, 2018
    Assignee: International Business Machines Corporation
    Inventors: Alain E. Biem, Dattaram Bijavara Aswathanarayana Rao, Bharath K. Devaraju
  • Patent number: 10127495
    Abstract: Systems and methods for reducing the size of deep neural networks are disclosed. In an embodiment, a server computer stores a plurality of training datasets, each of which comprise a plurality of training input matrices and a plurality of corresponding outputs. The server computer initiates training of a deep neural network using the plurality of training input matrices, a weight matrix, and the plurality of corresponding outputs. While the training of the deep neural network is being performed, the server computer identifies one or more weight values of the weight matrix for removal. The server computer removes the one or more weight values from the weight matrix to generate a reduced weight matrix. The server computer then stores the reduced weight matrix with the deep neural network.
    Type: Grant
    Filed: April 14, 2017
    Date of Patent: November 13, 2018
    Inventors: Rohan Bopardikar, Sunil Bopardikar
  • Patent number: 10127494
    Abstract: A circuit for performing neural network computations for a neural network is described. The circuit includes plurality of neural network layers each including a crossbar arrays. The plurality of crossbar arrays are formed in a common substrate in a stacked configuration. Each crossbar array includes a set of crosspoint devices. A respective electrical property of each of the crosspoint devices is adjustable to represent a weight value that is stored for each respective crosspoint device. A processing unit is configured to adjust the respective electrical properties of each of the crosspoint devices by pre-loading each of the crosspoint devices with a tuning signal. A value of the turning signal for each crosspoint device is a function of the weight value represented by each respective crosspoint device.
    Type: Grant
    Filed: August 2, 2017
    Date of Patent: November 13, 2018
    Assignee: Google LLC
    Inventors: Pierre-luc Cantin, Olivier Temam
  • Patent number: 10102478
    Abstract: Each computer of a peer-to-peer (P2P) network performs an iterative computer-based modeling task defined by a set of training data including at least some training data that are not accessible to the other computers of the P2P network, and by a set of parameters including a shared parameter. The modeling task optimizes an objective function comparing a model parameterized by the set of parameters with the training data. Each iteration includes: performing an iterative gradient step update of parameter values stored at the computer based on the objective function; receiving parameter values of the shared parameter from other computers of the P2P network; adjusting the parameter value of the shared parameter stored at the computer by averaging the received parameter values; and sending the parameter value of the shared parameter stored at the computer to other computers of the P2P network.
    Type: Grant
    Filed: June 26, 2015
    Date of Patent: October 16, 2018
    Assignee: Conduent Business Services, Inc.
    Inventors: Guillaume Bouchard, Julien Perez, James Brinton Henderson
  • Patent number: 10102254
    Abstract: A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for providing confidence rankings based on temporal semantics. Responsive to receiving an input question, a set of candidate answers is identified from a knowledge domain based on a correlation between an identified one or more predicates and an identified one or more arguments to the knowledge domain. A confidence score is associated with each of the candidate answers and each confidence score associated with each candidate answer is refined based on a set of temporal characteristics identified in the input question. A set of temporally refined candidate answers is then provided to the user.
    Type: Grant
    Filed: February 11, 2016
    Date of Patent: October 16, 2018
    Assignee: International Business Machines Corporation
    Inventors: John P. Bufe, III, Donna K. Byron, Alexander Pikovsky, Timothy P. Winkler
  • Patent number: 10095981
    Abstract: Methods, systems, and apparatus for solving optimization tasks. In one aspect, a method includes receiving input data comprising (i) data specifying an optimization task to be solved, and (ii) data specifying task objectives for solving the optimization task, comprising one or more local task objectives and one or more global task objectives; processing the received input data to obtain one or more initial solutions to the optimization task based on the local task objectives, wherein at least one initial solution is obtained from a first quantum computing resource; and processing the generated one or more initial solutions using a second quantum computing resource to generate a global solution to the optimization task based on the global task objectives.
    Type: Grant
    Filed: March 22, 2017
    Date of Patent: October 9, 2018
    Assignee: Accenture Global Solutions Limited
    Inventors: Daniel Garrison, Andrew E. Fano, Jurgen Albert Weichenberger
  • Patent number: 10095660
    Abstract: Various embodiments are generally directed to techniques for producing statistically correct and efficient combinations of multiple simulated posterior samples from MCMC and related Bayesian sampling schemes are described. One or more chains from a Bayesian posterior distribution of values may be generated. It may be determine whether the one or more chains have reached stationarity through parallel processing on a plurality of processing nodes. Based upon the determination, each of the one or more chains that have reached stationarity through parallel processing on the plurality of processing nodes may be sorted. The one or more sorted chains may be resampled through parallel processing on the plurality of processing nodes. The one or more resampled chains may be combined. Other embodiments are described and claimed.
    Type: Grant
    Filed: March 13, 2014
    Date of Patent: October 9, 2018
    Assignee: SAS Institute Inc.
    Inventors: Christian Macaro, Jan Chvosta, Mark Roland Little
  • Patent number: 10089581
    Abstract: A computer implemented data driven classification and data quality checking system is provided. The system has an interface application enabled to receive data and has an associative memory software. The system has a data driven associative memory model configured to categorize one or more fields of received data and to analyze the received data. The system has a data quality rating metric associated with the received data. The system has a machine learning data quality checker for the received data, and is configured to add the received data to a pool of neighboring data, if the data quality rating metric is greater than or equal to a data quality rating metric threshold. The machine learning data quality checker is configured to generate and communicate an alert of a potential error in the received data, if the data quality rating metric is less than the data quality rating metric threshold.
    Type: Grant
    Filed: June 30, 2015
    Date of Patent: October 2, 2018
    Assignee: The Boeing Company
    Inventors: Jaime A. Flores, Brian Warn, Danielle C. Young, Patrick N. Harris
  • Patent number: 10088815
    Abstract: A wire electric discharge machine according to the present invention includes a machine learning device which performs machine learning for adjustment of a machining condition of the wire electric discharge machine, the machine learning device includes a state observation unit which acquires data related to a machining state of a workpiece, a reward calculation unit which calculates a reward based on data related to a machining state, a machining condition adjustment learning unit which determines an adjustment amount of a machining condition based on a machine learning result and data related to a machining state, and a machining condition adjustment unit which adjusts a machining condition based on the determined adjustment amount of a machining condition, and the machining condition adjustment learning unit performs machine learning for adjustment of a machining condition based on the determined adjustment amount of a machining condition, data related to a machining state and acquired by the state observat
    Type: Grant
    Filed: August 26, 2016
    Date of Patent: October 2, 2018
    Assignee: FANUC CORPORATION
    Inventors: Mitsuharu Onodera, Kaoru Hiraga
  • Patent number: 10083153
    Abstract: An arithmetic processing apparatus performs arithmetic by a neural network in which multiple processing layers are hierarchically connected. The arithmetic processing apparatus corresponding to one of the multiple processing layers includes a convolution arithmetic portion and a pooling processing portion. The convolution arithmetic portion receives an input data from another of the plurality of processing layers, performs convolution arithmetic to the input data, and in each arithmetic cycle, outputs a part of all convolution arithmetic result data required for single pooling processing. The pooling processing portion performs the single pooling processing to the all convolution arithmetic result data before executing activation processing.
    Type: Grant
    Filed: March 31, 2015
    Date of Patent: September 25, 2018
    Assignee: DENSO CORPORATION
    Inventors: Tomoaki Ozaki, Kenichi Minoya
  • Patent number: 10083403
    Abstract: A method for improving accuracy and quality of received data is provided. The method provides a computer implemented data driven classification and data quality checking system. The method uses the associative memory software to build a data driven associative memory model that enables a machine learning data quality checker for receiving data. The method categorizes one or more fields of received data, analyzes the received data, and calculates a data quality rating metric, by comparing the received data with a pool of neighboring data in the category of field of the received data. The method accepts and adds the received data, if the data quality rating metric is greater than or equal to a data quality rating metric threshold, and generates and communicates an alert of a potential error in the received data, if the data quality rating metric is less than the data quality rating metric threshold.
    Type: Grant
    Filed: June 30, 2015
    Date of Patent: September 25, 2018
    Assignee: The Boeing Company
    Inventors: Jaime A. Flores, Brian Warn, Danielle C. Young, Patrick N. Harris
  • Patent number: 10068172
    Abstract: A system and method is disclosed for knowledge engineering using a computerized graphical editor to manage and create knowledge-based systems containing a navigable graph of modal pages with conditional content and user interface knowledge. The invention enables the entire knowledge engineering workflow to be performed within a non-technical graphical environment and without requiring a computer programming or mathematical background. Further, the presentation of knowledge as modal pages allows for simple ontological discovery and end-user player operation. Once editing is complete, the method allows for the set of pages, variables, and settings of which the knowledge-based system is composed to be exported into an independently executable knowledge-based system player containing an embedded inference engine.
    Type: Grant
    Filed: August 29, 2013
    Date of Patent: September 4, 2018
    Assignee: IfWizard Corporation
    Inventor: Dominic Sellers-Blais
  • Patent number: 10055683
    Abstract: A plurality of synapse determination circuits are provided on a one-to-one basis for a plurality of gate electrodes of a multi-input gate electrode in a neuron element. With respect to first image regions where “1” is repeatedly inputted in correspondence with group information, the synapse determination circuits corresponding to the first image regions are excitatory synapses. With respect to second image regions where “0” is repeatedly inputted in correspondence with the group information, the synapse determination circuits corresponding to the second image regions are inhibitory synapses.
    Type: Grant
    Filed: August 11, 2014
    Date of Patent: August 21, 2018
    Assignee: DENSO CORPORATION
    Inventor: Hitoshi Yamaguchi
  • Patent number: 10049162
    Abstract: A system and method for processing information in unstructured or structured form, comprising a computer running in a distributed network with one or more data agents. Associations of natural language artifacts may be learned from natural language artifacts in unstructured data sources, and semantic and syntactic relationships may be learned in structured data sources, using grouping based on a criteria of shared features that are dynamically determined without the use of a priori classifications, by employing conditional probability constraints.
    Type: Grant
    Filed: November 6, 2015
    Date of Patent: August 14, 2018
    Assignee: Digital Reasoning Systems, Inc.
    Inventor: Timothy W. Estes
  • Patent number: 10042654
    Abstract: A method for distributing sets of regular expressions to a fixed number of state machine engines includes combining, with a processing device, a plurality of regular expressions into a single compound regular expression, creating a single nondeterministic finite automaton (NFA) including a plurality of NFA states based on the compound regular expression, performing an interference analysis for each pair of NFA states to identify all pairs of NFA states that would potentially interfere in an equivalent deterministic finite automaton (DFA), creating an interference graph representing the regular expressions associated with potentially interfering NFA states based on the results of the interference analysis, and performing a graph coloring algorithm on the interference graph to assign a different color to each represented regular expression in the graph.
    Type: Grant
    Filed: June 10, 2014
    Date of Patent: August 7, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventor: Christoph Angerer
  • Patent number: 10019674
    Abstract: A machine learning apparatus includes a state observing unit for observing a state variable comprised of at least one of an actual dimension value, a resistance actual value, etc., and at least one of a dimension command value, a resistance command value, etc., and an execution time command value for a program, and a learning unit for performing a learning operation by linking at least one of an actual dimension value, a resistance actual value, etc., to at least one of a dimension command value, a resistance command value, etc., observed by the state observing unit, and an execution time command value for the program.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: July 10, 2018
    Assignee: FANUC CORPORATION
    Inventor: Yasunori Sugimoto
  • Patent number: 10013658
    Abstract: A control device in a vehicle includes a unit for calculating, during operation of the vehicle, on the basis of at least one input variable ascertained during operation, at least one output variable for a control system of functions of the vehicle. The control device performs the calculation of the output variables using a Bayesian regression of training values ascertained, before operation, for the output variable and the input variable.
    Type: Grant
    Filed: April 6, 2011
    Date of Patent: July 3, 2018
    Assignee: ROBERT BOSCH GMBH
    Inventors: Felix Streichert, Tobias Lang, Heiner Markert, Axel Aue, Thomas Kruse, Volker Imhof, Thomas Richardsen, Ulrich Schulmeister, Nico Bannow, Rene Diener, Ernst Kloppenburg, Michael Saetzler, Holger Ulmer
  • Patent number: 10004112
    Abstract: A machine learning apparatus includes a state observing unit and a learning unit. The state observing unit observes a state variable comprised of at least one of an adhesion state, a dielectric strength voltage, an electric heating time temperature, and an actual electric heating time value of a coil electrically heated by a coil electric heating unit, and at least one of an electric heating time command value, a voltage, and a current in the coil electric heating unit. The learning unit performs a learning operation by linking at least one of an adhesion state, a dielectric strength voltage, an electric heating time temperature, and an actual electric heating time value of the coil observed by the state observing unit to at least one of the electric heating time command value, the voltage, and the current, which are observed by the state observing unit.
    Type: Grant
    Filed: September 29, 2016
    Date of Patent: June 19, 2018
    Assignee: FANUC CORPORATION
    Inventor: Yasunori Sugimoto
  • Patent number: 9996799
    Abstract: A method and associated systems automatically convert source code of a legacy computer program into a target application by generating an intermediary, context-sensitive, business-process model that represents logic of the legacy system. A set of business rules are inferred from the source code. Each rule is modified by a first generation of additional conditions inferred from context of the source code and of the rule. The rule continues to be further refined by successive generations of context-dependent conditions, identifying each generation of conditions from the context of the preceding generation. This procedure repeats until no more levels of context can be identified. The rule is then imported into the business-process model as a logical data structure. Logic represented by the resulting model is used to generate source code of the target application.
    Type: Grant
    Filed: May 20, 2016
    Date of Patent: June 12, 2018
    Assignee: International Business Machines Corporation
    Inventors: James E. Bostick, John M. Ganci, Jr., Paul E. Hensler, Craig M. Trim