The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jul. 14, 2026

Filed:

Sep. 30, 2021
Applicant:

Amazon Technologies, Inc., Seattle, WA (US);

Inventors:

Xiaodan Tan, Santa Clara, CA (US);

Paul Gilbert Meyer, Jericho, VT (US);

Gennady Pekhimenko, Oakville, CA;

Randy Renfu Huang, Morgan Hill, CA (US);

Assignee:

Amazon Technologies, Inc., Seattle, WA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/0495 (2023.01); G06N 3/04 (2023.01); G06N 3/082 (2023.01);
U.S. Cl.
CPC ...
G06N 3/082 (2013.01); G06N 3/04 (2013.01);
Abstract

Techniques for compressing a neural network model by mixing compression ratios (sparsity patterns) are described. The weight tensor of a neural network model is divided into weight groups. The pruning cost of compressing the weight values according to a compression ratio is determined for each weight group, and a pruning cost distribution for the compression ratio is generated from the pruning costs of the weight groups. A cost threshold can then be selected from the pruning cost distribution, and weight groups having a pruning cost below the selected cost threshold are compressed according to the compression ratio. The remaining weight groups can be compressed using one or more less aggressive compression ratios. The cost threshold can be adjusted to tune the overall sparsity and accuracy of the compressed neural network.


Find Patent Forward Citations

Loading…