Patents by Inventor Sergey Serebryakov

Sergey Serebryakov has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20200073755
    Abstract: A computer system includes multiple memory array components that include respective analog memory arrays which are sequenced to implement a multi-layer process. An error array data structure is obtained for at least a first memory array component, and from which a determination is made as to whether individual nodes (or cells) of the error array data structure are significant. A determination can be made as to any remedial operations that can be performed to mitigate errors of significance.
    Type: Application
    Filed: August 28, 2018
    Publication date: March 5, 2020
    Inventors: John Paul Strachan, Catherine Graves, Dejan S. Milojicic, Paolo Faraboschi, Martin Foltin, Sergey Serebryakov
  • Publication number: 20200042287
    Abstract: Disclosed techniques provide for dynamically changing precision of a multi-stage compute process. For example, changing neural network (NN) parameters on a per-layer basis depending on properties of incoming data streams and per-layer performance of an NN among other considerations. NNs include multiple layers that may each be calculated with a different degree of accuracy and therefore, compute resource overhead (e.g., memory, processor resources, etc.). NNs are usually trained with 32-bit or 16-bit floating-point numbers. Once trained, an NN may be deployed in production. One approach to reduce compute overhead is to reduce parameter precision of NNs to 16 or 8 for deployment. The conversion to an acceptable lower precision is usually determined manually before deployment and precision levels are fixed while deployed.
    Type: Application
    Filed: August 1, 2018
    Publication date: February 6, 2020
    Inventors: Sai Rahul Chalamalasetti, Paolo Faraboschi, Martin Foltin, Catherine Graves, Dejan S. Milojicic, Sergey Serebryakov, John Paul Strachan
  • Patent number: 10452472
    Abstract: A dot-product engine (DPE) implemented on an integrated circuit as a crossbar array (CA) includes memory elements comprising a memristor and a transistor in series. A crossbar with N rows, M columns may have N×M memory elements. A vector input for N voltage inputs to the CA and a vector output for M voltage outputs from the CA. An analog-to-digital converter (ADC) and/or a digital-to-analog converter (DAC) may be coupled to each input/output register. Values representing a first matrix may be stored in the CA. Voltages/currents representing a second matrix may be applied to the crossbar. Ohm's Law and Kirchoff's Law may be used to determine values representing the dot-product as read from the crossbar. A portion of the crossbar may perform Error-correcting Codes (ECC) concurrently with calculating the dot-product results. ECC codes may be used to only indicate detection of errors, or for both detection and correction of results.
    Type: Grant
    Filed: June 4, 2018
    Date of Patent: October 22, 2019
    Assignee: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
    Inventors: Catherine Graves, John Paul Strachan, Dejan S. Milojicic, Paolo Faraboschi, Martin Foltin, Sergey Serebryakov
  • Patent number: 8892343
    Abstract: Systems and methods are provided for determining an impact of a planned event. Traffic flow velocity is measured at each of a plurality of traffic sensors over a period of time before the planned event, with each traffic sensor having an associated geographical location. A plurality of measured traffic flow velocities for each traffic sensor are stored on a non-transitory computer readable medium. A traffic flow velocity at each traffic sensor is measured at each of a plurality of representative times within a defined time period including a known start time and an expected end time of the event. A threshold velocity is calculated from the stored traffic flow velocities for each traffic sensor corresponding to each representative time. For each representative time, a set of traffic sensors is determined at which the measured traffic flow velocity during the defined time period is less than the threshold velocity.
    Type: Grant
    Filed: July 31, 2012
    Date of Patent: November 18, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Chetan Kumar Gupta, Sergey Serebryakov, Maria G Castellanos
  • Publication number: 20140039782
    Abstract: Systems and methods are provided for determining an impact of a planned event. Traffic flow velocity is measured at each of a plurality of traffic sensors over a period of time before the planned event, with each traffic sensor having an associated geographical location. A plurality of measured traffic flow velocities for each traffic sensor are stored on a non-transitory computer readable medium. A traffic flow velocity at each traffic sensor is measured at each of a plurality of representative times within a defined time period including a known start time and an expected end time of the event. A threshold velocity is calculated from the stored traffic flow velocities for each traffic sensor corresponding to each representative time. For each representative time, a set of traffic sensors is determined at which the measured traffic flow velocity during the defined time period is less than the threshold velocity.
    Type: Application
    Filed: July 31, 2012
    Publication date: February 6, 2014
    Inventors: Chetan Kumar Gupta, Sergey Serebryakov, Maria G. Castellanos