Patent · US Active

Method for neuromorphic implementation of convolutional neural networks

US10387774B1 · kind B1 · utility

7Cited by

0References

19Claims

0Family size

Assignee

HRL Laboratories, LLC · US

Inventors

Yongqiang Cao · Portland, US
Yang Chen · Westlake Village, US
Deepak Khosla · Camarillo, US

Key dates

Filing date	Jan 30, 2015
Grant date	Aug 20, 2019
Priority date	—
Expiry date	Jun 27, 2037

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/088
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Described is a system for converting convolutional neural networks to spiking neural networks. A convolutional neural network (CNN) is adapted to fit a set of requirements of a spiking neural network (SNN), resulting in an adapted CNN. The adapted CNN is trained to obtain a set of learned weights, and the set of learned weights is then applied to a converted SNN having an architecture similar to the adapted CNN. The converted SNN is then implemented on neuromorphic hardware, resulting in reduced power consumption.

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