Method and apparatus for universal pruning and compression of deep convolutional neural networks under joint sparsity constraints
US11423312B2 · kind B2 · utility
3Cited by
3References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 25, 2018 |
| Grant date | Aug 23, 2022 |
| Priority date | — |
| Expiry date | Jun 24, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/0495
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and system for constructing a convolutional neural network (CNN) model are herein disclosed. The method includes regularizing spatial domain weights, providing quantization of the spatial domain weights, pruning small or zero weights in a spatial domain, fine-tuning a quantization codebook, compressing a quantization output from the quantization codebook, and decompressing the spatial domain weights and using either sparse spatial domain convolution and sparse Winograd convolution after pruning Winograd-domain weights.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.