Patents by Inventor Viktor Sergeevich LEMPICZKIJ

Viktor Sergeevich LEMPICZKIJ 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).

  • Training of deep neural networks on the basis of distributions of paired similarity measures
    Patent number: 11488012
    Abstract: This technical solution generally refers to computing systems based on biological models, and specifically to ways of training deep neural networks based on distributions of the pairwise similarity measures.
    Type: Grant
    Filed: December 30, 2016
    Date of Patent: November 1, 2022
    Assignee: OBSCHESTVO S OGRANICHENNOY OTVETSTVENNOSTYU “VIZHNLABS”
    Inventors: Evgeniya Sergeevna Ustinova, Viktor Sergeevich Lempiczkij
  • TRAINING OF DEEP NEURAL NETWORKS ON THE BASIS OF DISTRIBUTIONS OF PAIRED SIMILARITY MEASURES
    Publication number: 20200218971
    Abstract: This technical solution generally refers to computing systems based on biological models, and specifically to ways of training deep neural networks based on distributions of the pairwise similarity measures.
    Type: Application
    Filed: December 30, 2016
    Publication date: July 9, 2020
    Inventors: Evgeniya Sergeevna USTINOVA, Viktor Sergeevich LEMPICZKIJ