Patents by Inventor Vassileios POTHOS

Vassileios POTHOS 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).

  • PARSIMONIOUS INFERENCE ON CONVOLUTIONAL NEURAL NETWORKS
    Publication number: 20220253711
    Abstract: The disclosed system incorporates a new learning module, the Learning Kernel Activation Module (LKAM), at least serving the purpose of enforcing the utilization of less convolutional kernels by learning kernel activation rules and by actually controlling the engagement of various computing elements: The exemplary module activates/deactivates a sub-set of filtering kernels, groups of kernels, or groups of full connected neurons, during the inference phase, on-the-fly for every input image depending on the input image content and the learned activation rules.
    Type: Application
    Filed: April 29, 2022
    Publication date: August 11, 2022
    Inventors: Ilias THEODORAKOPOULOS, Vassileios POTHOS, Dimitris KASTANIOTIS, Nikos FRAGOULIS
  • Parsimonious inference on convolutional neural networks
    Patent number: 11321613
    Abstract: The disclosed system incorporates a new learning module, the Learning Kernel Activation Module (LKAM), at least serving the purpose of enforcing the utilization of less convolutional kernels by learning kernel activation rules and by actually controlling the engagement of various computing elements: The exemplary module activates/deactivates a sub-set of filtering kernels, groups of kernels, or groups of full connected neurons, during the inference phase, on-the-fly for every input image depending on the input image content and the learned activation rules.
    Type: Grant
    Filed: November 16, 2017
    Date of Patent: May 3, 2022
    Assignee: IRIDA LABS S.A.
    Inventors: Ilias Theodorakopoulos, Vassileios Pothos, Dimitris Kastaniotis, Nikos Fragoulis
  • PARSIMONIOUS INFERENCE ON CONVOLUTIONAL NEURAL NETWORKS
    Publication number: 20180137417
    Abstract: The disclosed system incorporates a new learning module, the Learning Kernel Activation Module (LKAM), at least serving the purpose of enforcing the utilization of less convolutional kernels by learning kernel activation rules and by actually controlling the engagement of various computing elements: The exemplary module activates/deactivates a sub-set of filtering kernels, groups of kernels, or groups of full connected neurons, during the inference phase, on-the-fly for every input image depending on the input image content and the learned activation rules.
    Type: Application
    Filed: November 16, 2017
    Publication date: May 17, 2018
    Inventors: Ilias THEODORAKOPOULOS, Vassileios POTHOS, Dimitris KASTANIOTIS, Nikos FRAGOULIS