logo

For the Inventor, By the Inventor

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.

Patent No.:

US 10832136 B1

PDFFull Text
Date of Patent:
Nov. 10, 2020

Filed:

May. 09, 2017

Passive pruning of filters in a convolutional neural network

Applicant:

Nec Laboratories America, Inc., Princeton, NJ (US);

Inventors:

Asim Kadav, Jersey City, NJ (US);

Igor Durdanovic, Lawrenceville, NJ (US);

Hans Peter Graf, Lincroft, NJ (US);

Hao Li, Silver Spring, MD (US);

Assignee:

NEC Corporation, , JP;

Attorney:

Joseph Kolodka

Primary Examiner:

Eric Nilsson

Assistant Examiner:

Yao David Huang

Int. Cl.
CPC ...
G06N 3/08 (2006.01); G06N 3/04 (2006.01); G06K 9/62 (2006.01); G06K 9/00 (2006.01); G06K 9/46 (2006.01); G08B 13/00 (2006.01); G08B 29/18 (2006.01); G06F 17/15 (2006.01); G06F 17/17 (2006.01); G06K 9/66 (2006.01); G06N 5/04 (2006.01);
U.S. Cl.
CPC ...
G06N 3/082 (2013.01); G06F 17/153 (2013.01); G06F 17/17 (2013.01); G06K 9/00771 (2013.01); G06K 9/4628 (2013.01); G06K 9/627 (2013.01); G06K 9/6228 (2013.01); G06K 9/6296 (2013.01); G06K 9/66 (2013.01); G06N 3/0454 (2013.01); G08B 13/00 (2013.01); G08B 29/186 (2013.01); G06K 2009/00738 (2013.01); G06N 3/0427 (2013.01); G06N 3/0481 (2013.01); G06N 5/045 (2013.01); H03H 2222/04 (2013.01);
Abstract

Methods and systems for pruning a convolutional neural network (CNN) include calculating a sum of weights for each filter in a layer of the CNN. The filters in the layer are sorted by respective sums of weights. A set of m filters with the smallest sums of weights is filtered to decrease a computational cost of operating the CNN. The pruned CNN is retrained to repair accuracy loss that results from pruning the filters.

Find Patent Forward Citations

Kadav, Asim. (2020). Passive pruning of filters in a convolutional neural network (U.S. Patent No. 10832136). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/10832136

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…