Patent · US Active

Apparatus and method for executing reversal training of artificial neural network

US10713568B2 · kind B2 · utility

1Cited by
0References
24Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 14, 2019
Grant dateJul 14, 2020
Priority date
Expiry dateJun 14, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/01
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An apparatus for executing backpropagation of an artificial neural network comprises an instruction caching unit, a controller unit, a direct memory access unit, an interconnection unit, a master computation module, and multiple slave computation modules. For each layer in a multilayer neural network, weighted summation may be performed on input gradient vectors to calculate an output gradient vector of this layer. The output gradient vector may be multiplied by a derivative value of a next-layer activation function on which forward operation is performed, so that a next-layer input gradient vector can be obtained. The input gradient vector may be multiplied by an input neuron counterpoint in forward operation to obtain the gradient of a weight value of this layer, and the weight value of this layer can be updated according to the gradient of the obtained weight value of this layer.

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