Method and system for hierarchical weight-sparse convolution processing
US11144823B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 5, 2021 |
| Grant date | Oct 12, 2021 |
| Priority date | — |
| Expiry date | Apr 5, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/048
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for hierarchical weight-sparse convolution processing are described. An exemplary method comprises: obtaining an input tensor and a filter at a convolution layer of a neural network; segmenting the filter into a plurality of sub-filters; generating a hierarchical bit representation of the filter representing a plurality of non-zero weights in the filter, wherein the hierarchical bit representation comprises a first layer, the first layer comprising a plurality of bits respectively corresponding to the plurality of sub-filters in the filter, each of the plurality of bits indicating whether the corresponding sub-filter includes at least one non-zero weight; and performing multiply-and-accumulate (MAC) operations based on the hierarchical bit representation of the filter and the input tensor.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.