Pruning method, device and apparatus of artificial neural network and readable storage medium

Abstract

The invention discloses a pruning method, device and apparatus of an artificial neural network and a readable storage medium. The pruning method comprises: calculating according to a Taylor's formulacarrying a remainder to obtain contribution values of neurons in the artificial neural network; removing the corresponding neurons in the artificial neural network according to the sequence of the contribution values until the quantity of the removed neurons reaches a first preset threshold; using a pre-stored first dataset to train the artificial neural network with the neurons removed. Calculating is performed with the Taylor's formula carrying the remainder to obtain contribution values of neurons in the artificial neural network, the contribution values are closer to real contribution values than those in the artificial neural network which are obtained by performing calculating with a non-remainder Taylor's formula in the prior art; therefore, being pruned according to contribution values, obtained by performing calculating via the Taylor's formula carrying the remainder, the artificial neural network is more precise with precision loss reduced.

Description

technical field [0001] The invention relates to the technical field of artificial neural networks, in particular to an artificial neural network pruning method. The invention also relates to an artificial neural network pruning device, equipment and readable storage medium. Background technique [0002] Artificial neural network is an algorithmic mathematical model that imitates the behavior characteristics of animal neural networks and performs distributed parallel information processing. It has been widely used in data mining, web mining, bioinformatics and multimedia data processing and other fields. [0003] Generally speaking, artificial neural network consists of three layers, namely input layer, hidden layer and output layer. The number of nodes in the hidden layer generally depends on the complexity of the problem. A neural network with a large number of hidden nodes can learn quickly and can avoid the system from falling into local minima, but the generalization ab...

AI Technical Summary

Problems solved by technology

The pruning method in the prior art is to calculate the contribution value of each neuron through the first-order Taylor formula without remainder, because the value calculated by the first-order Taylor formula without remainder is an approximate value, not every The real contribution value of each neuron, so the network pruned by the pruning method of the prior art will have errors in actual use, thus making the accuracy of the network low.

Images