Patents by Inventor Kasanagottu Sai Ram

Kasanagottu Sai Ram 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).

  • METHOD FOR AUTOMATIC HYBRID QUANTIZATION OF DEEP ARTIFICIAL NEURAL NETWORKS
    Publication number: 20230385645
    Abstract: A method includes, for each floating-point layer in a set of floating-point layers: calculating a set of input activations and a set of output activations of the floating-point layer; converting the floating-point layer to a low-bit-width layer; calculating a set of low-bit-width output activations based on the set of input activations; and calculating a per-layer deviation statistic of the low-bit-width layer. The method also includes ordering the set of low-bit-width layers based on the per-layer deviation statistic of each low-bit-width layer.
    Type: Application
    Filed: August 9, 2023
    Publication date: November 30, 2023
    Inventors: Wajahat Qadeer, Rehan Hameed, Satyanarayana Raju Uppalapati, Abhilash Bharath Ghanore, Kasanagottu Sai Ram
  • Method for automatic hybrid quantization of deep artificial neural networks
    Patent number: 11763158
    Abstract: A method includes, for each floating-point layer in a set of floating-point layers: calculating a set of input activations and a set of output activations of the floating-point layer; converting the floating-point layer to a low-bit-width layer; calculating a set of low-bit-width output activations based on the set of input activations; and calculating a per-layer deviation statistic of the low-bit-width layer. The method also includes ordering the set of low-bit-width layers based on the per-layer deviation statistic of each low-bit-width layer.
    Type: Grant
    Filed: December 4, 2020
    Date of Patent: September 19, 2023
    Assignee: Deep Vision Inc.
    Inventors: Wajahat Qadeer, Rehan Hameed, Satyanarayana Raju Uppalapati, Abhilash Bharath Ghanore, Kasanagottu Sai Ram
  • METHOD FOR AUTOMATIC HYBRID QUANTIZATION OF DEEP ARTIFICIAL NEURAL NETWORKS
    Publication number: 20210174172
    Abstract: A method includes, for each floating-point layer in a set of floating-point layers: calculating a set of input activations and a set of output activations of the floating-point layer; converting the floating-point layer to a low-bit-width layer; calculating a set of low-bit-width output activations based on the set of input activations; and calculating a per-layer deviation statistic of the low-bit-width layer. The method also includes ordering the set of low-bit-width layers based on the per-layer deviation statistic of each low-bit-width layer.
    Type: Application
    Filed: December 4, 2020
    Publication date: June 10, 2021
    Inventors: Wajahat Qadeer, Rehan Hameed, Satyanarayana Raju Uppalapati, Abhilash Bharath Ghanore, Kasanagottu Sai Ram