Patent · US Active

Generating larger neural networks

US10699191B2 · kind B2 · utility

5Cited by

0References

20Claims

0Family size

Assignee

Google LLC · US

Inventors

Ian Goodfellow · Mountain View, US
Tianqi Chen · Seattle, US
Jonathan Shlens · San Francisco, US

Key dates

Filing date	Nov 11, 2016
Grant date	Jun 30, 2020
Priority date	—
Expiry date	Jul 14, 2038

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/09
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

This specification describes methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a larger neural network from a smaller neural network. One of the described methods includes obtaining data specifying an original neural network and generating a larger neural network from the original neural network The larger neural network has a larger neural network structure than the original neural network structure. The values of the parameters of the original neural network units and the additional neural network units are initialized so that the larger neural network generates the same outputs from the same inputs as the original neural network and the larger neural network is trained to determine trained values of the parameters of the original neural network units and the additional neural network units from the initialized values.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.