Self-adaptive learning neural network implementation method based on evolutionary algorithm

Abstract

The invention relates to the field of neural network computing technologies, and is a self-adaptive learning neural network implementation method based on an evolutionary algorithm. One or more types of known neural networks are used as an initial parent of the evolutionary algorithm; and characteristics of the neural networks which are the initial parent are integrated by using the evolutionary algorithm, so as to obtain an optimum output value. According to the invention, binary coding is performed on a circuit implemented by the neural networks, a result obtained by coding is used as a chromosome of an individual; and chromosomes constitute a primitive population of an organism, that is, the initial parent. According to the invention, a case in a conventional method that only the evolutionary algorithm is used to optimize a neural network weight is broken through; optimization for modes such as a neural network organization form, a connection weight among networks, and a network calculation method is simultaneously implemented by using the evolutionary algorithm; a network freedom degree is increased; an optimization scope is enlarged; and a relatively simple network is initially obtained; and in acquired learning, network complexity is increased by using an algorithm.

Description

technical field [0001] The invention belongs to the technical field of neural network calculations, and relates to the realization of various learnable neural network structures and the optimization of evolutionary algorithms in network calculations, in particular to a method for realizing self-adaptive learning neural networks based on evolutionary algorithms. Background technique [0002] The current research on neural networks can be roughly divided into three mainstream structural models: Perceptron neural network, Back-propagate neural network and Deep Learning neural network. Each network has its own characteristics. In terms of overall performance, the deep learning network performs better than the other two in image recognition. [0003] The perceptual neural network only has a three-layer structure. The first layer usually abstracts the characteristics of the target artificially. The second layer is a computing network. The weight of the features abstracted by the f...

AI Technical Summary

Problems solved by technology

However, in terms of the implementation structure, the complexity of the deep learning network is relatively high, and the recognition accuracy has a great relationship with the number of training

Images