Neural network training method, neural network training device, data processing method and data processing device

Abstract

The invention provides a neural network training method, a neural network training device, a data processing method and a data processing device. The neural network training method comprises the following steps: S210, transforming a set of initial convolution kernels corresponding to each of at least one set of convolution layers of a convolutional neural network into a corresponding set of transformed convolution kernels by use of a low-rank approximation method; S220, training the convolutional neural network based on the transformed convolution kernels corresponding to the at least one set of convolution layers; S230, judging whether the trained convolutional neural network meets a predetermined standard, going to S240 if the trained convolutional neural network meets the predetermined standard, or going to S250; S240, decomposing the product of the set of trained convolution kernels corresponding to each of the at least one set of convolution layers into a corresponding set of compressed convolution kernels; and S250, taking the set of trained convolution kernels corresponding to each of the at least one set of convolution layers as a set of initial convolution kernels corresponding to the set of convolution layers, and returning to S210. Through the methods and the devices, the amount of computation can be saved.

Description

technical field [0001] The present invention relates to the field of computers, and more particularly to a neural network training method and device and a data processing method and device. Background technique [0002] Convolutional neural networks have been widely used in text recognition, speech recognition and other fields. In order to improve the accuracy of the output results of the convolutional neural network, a common method is to increase the number of channels in the intermediate results. However, since the amount of computation is positively correlated with the number of channels, this inevitably increases the amount of computation. On platforms with limited computing power such as mobile phones, the large amount of computing will not only cause long delays, but also bring challenges in terms of power consumption and heat dissipation. SUMMARY OF THE INVENTION [0003] The present invention has been made in view of the above-mentioned problems. The present in...

AI Technical Summary

Problems solved by technology

However, since the amount of calculation is positively correlated with the number of channels, this inevitably increases the amount of calculation

On platforms with limited computing power such as mobile phones, large calculations will not only cause long delays, but also bring challenges in terms of power consumption and heat dissipation.

Images