Method for improving BP (back propagation) neutral network and based on genetic algorithm

Abstract

The invention discloses a method for improving a BP (back propagation) neutral network and based on a genetic algorithm. The method includes coding the BP network to determine structure of the neutral network, wherein the structure includes the number of hidden layers and the number of units of each layer; adopting real-number coding to code by taking weight and threshold as genes, wherein each neutral network corresponds to a chromosome after coding; using the genetic algorithm to perform selection optimization on the network, wherein selection optimization includes the steps of selection, crossing and variation; training the BP network to acquire a final result; decoding an optimal individual selected by the genetic algorithm to generate a new neutral network, and training the new network by applying a BP training algorithm to acquire a final result. The method combines the genetic algorithm with the BP network, thereby being capable of fully utilizing advantages of the both, the problem that initial weight and threshold of the BP network are difficult to determine can be solved, searching range can be narrowed, training speed of the BP network can be increased, and the problem of local minimum can be improved.

Description

technical field [0001] The invention relates to an artificial neural network, in particular to a method for improving a BP neural network based on a genetic algorithm. Background technique [0002] The artificial neural network is developed from the biological neural network, which is the simplification, abstraction and simulation of the human brain or some basic characteristics. Its purpose is to simulate some mechanisms and mechanisms of the brain to achieve some specific functions. [0003] Among them, BP neural network, as the most widely used neural network model, has many practical applications in handwriting recognition, speech recognition, face recognition and biomedical signal processing. [0004] BP neural network, also known as error reverse broadcast network, is a multi-layer forward network, generally including an input layer, an output layer and one or more hidden layers, such as figure 1 shown. The BP neural network is a learning network with a tutor, which...

AI Technical Summary

Problems solved by technology

[0005] BP neural network is the most widely used algorithm in artificial neural network. Many effective learning algorithms have been proposed, but there are still some defects: ①The learning convergence speed is too slow; ②The gradient descent method used by BP neural network corrects weights and thresholds, There is a local minimum problem, which cannot guarantee convergence to the global minimum point; ③The number of hidden layers and the number of hidden layer units are not easy to determine

Although various improved learning algorithms can improve the convergence speed of the BP neural network, they are still not perfect in practical applications and cannot completely overcome the inherent defects of the BP algorithm.

④The selection of network structure, initial connection weights and thresholds has a great influence on network training, but it is impossible to accurately obtain

Images