Intellectual Property India Publishes Patent Application for 'Training Ultra-Large-Scale Vision Transformer Neural Networks' Filed by Google Llc

MUMBAI, India, Aug. 8 -- Intellectual Property India has published a patent application (202517067030 A) filed by Google Llc, Mountain View, U.S.A., on July 14, for 'training ultra-large-scale vision transformer neural networks.'

Inventor(s) include Dehghani, Mostafa; Djolonga, Josip; Heek, Jonathan; Mustafa, Basil; Padlewski, Piotr Michal; Gilmer, Justin Morgan; and Houlsby, Neil Matthew Tinmouth.

The application for the patent was published on Aug. 8, under issue no. 32/2025.

According to the abstract released by the Intellectual Property India: "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing an input through each of a plurality of layers of a neural network to generate an output using a plurality of hardware accelerators. The plurality of layers comprise a fully connected layer having a plurality of parameters arranged in a row dimension and a column dimension. One of the methods comprises: generating a plurality of parameter blocks by partitioning the plurality of parameters along the row dimension and the column dimension; determining a ratio of a number of parameters along the row dimension relative to a number of parameters along the column dimension; and determining whether to use row sharding or column sharding with the plurality of hardware accelerators to calculate an output for the fully connected layer and then calculating the output for the fully connected layer using either row sharding or column sharding."

The patent application was internationally filed on Jan. 26, 2024, under International application No.PCT/US2024/013200.

Disclaimer: Curated by HT Syndication.