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:
Mar. 24, 2020

Filed:

Dec. 14, 2018
Applicant:

Uber Technologies, Inc., San Francisco, CA (US);

Inventors:

Felipe Petroski Such, San Francisco, CA (US);

Jeffrey Michael Clune, San Francisco, CA (US);

Kenneth Owen Stanley, San Francisco, CA (US);

Edoardo Conti, San Francisco, CA (US);

Vashisht Madhavan, San Francisco, CA (US);

Joel Anthony Lehman, San Francisco, CA (US);

Assignee:

Uber Technologies, Inc., San Francisco, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 3/04 (2006.01); G06N 3/08 (2006.01); G06N 3/00 (2006.01); G06N 3/12 (2006.01);
U.S. Cl.
CPC ...
G06N 3/04 (2013.01); G06N 3/008 (2013.01); G06N 3/08 (2013.01); G06N 3/082 (2013.01); G06N 3/084 (2013.01); G06N 3/086 (2013.01); G06N 3/126 (2013.01);
Abstract

A source system initializes, using an initialization seed, a first parameter vector representing weights of a neural network. The source system determines a second parameter vector by performing a sequence of mutations on the first parameter vector, the mutations each being based on a perturbation seed. The source system generates, and stores to memory, an encoded representation of the second parameter vector that comprises the initialization seed and a sequence of perturbation seeds corresponding to the sequence of mutations. The source system transmits the data structure to a target system, which processes a neural network based on the data structure.


Find Patent Forward Citations

Petroski Such, Felipe. (2020). Scalable parameter encoding of artificial neural networks obtained via an evolutionary process (U.S. Patent No. 10599975). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/10599975

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

Loading…