Neural network training method and related products

Abstract

The invention provides a neural network training method executed on an integrated circuit chip device and a related product. The neural network comprises multiple layers, the method comprises the following steps of receiving a training instruction, determining the first-layer input data and the first-layer weight data according to the training instruction, and using the computing device to executen-layer forward operation of the neural network through the first-layer input data and the first-layer weight data to obtain an nth output result; obtaining the nth output result gradient according to the nth output result, obtaining the nth reverse operation of the nth layer of reverse operation according to the training instruction, and obtaining the nth reverse operation complexity by the computing device according to the nth output result gradient, the nth layer of input data, the nth layer of weight group data and the nth reverse operation. The technical scheme provided by the inventionhas the advantages of small calculated amount and low power consumption.

Description

technical field [0001] The present disclosure relates to the field of neural networks, in particular to a neural network training method and related products. Background technique [0002] Artificial Neural Network (ANN) is a research hotspot in the field of artificial intelligence since the 1980s. It abstracts the human brain neuron network from the perspective of information processing, establishes a simple model, and forms different networks according to different connection methods. In engineering and academia, it is often referred to directly as a neural network or a neural network. A neural network is an operational model consisting of a large number of nodes (or neurons) connected to each other. The operation of the existing neural network is based on CPU (Central Processing Unit, central processing unit) or GPU (English: Graphics Processing Unit, graphics processing unit) to realize the forward operation of neural network, the calculation amount of this kind of for...

AI Technical Summary

Problems solved by technology

The operation of the existing neural network is based on CPU (Central Processing Unit, central processing unit) or GPU (English: Graphics Processing Unit, graphics processing unit) to realize the forward operation of neural network, the calculation amount of this kind of forward operation is large, high power consumption

Images