Pattern recognition method based on self-adaptation correction neural network

Abstract

The invention relates to the field of pattern recognition, in particular to a pattern recognition method based on a self-adaptation correction neural network. The method comprises the steps of classifying input training samples through a probabilistic neural network model so as to obtain samples accurate in classification and samples inaccurate in classification; adding an input layer, a central layer and an excitation layer on the basis of the probabilistic neural network model structure so as to construct a self-adaptation correction neural network model structure; for the samples inaccurate in classification in the probabilistic neural network model, using themself as central points, calculating the allowance radius between the the samples and samples of other classifications, clustering error samples of same category so as to realize batch correction of classification patterns and replanning of a judging interface and build the self-adaptation correction neural network; finally, conducting pattern recognition on input testing samples based on the self-adaptation correction neural network model. The pattern recognition method has the advantages of being high in accuracy in mode classification, strong in mode generalization ability, good in classification real-time performance, wide in application prospect, and the like.

Description

technical field [0001] The invention belongs to the field of pattern recognition, in particular to a pattern recognition method based on an adaptive correction neural network. Background technique [0002] As a pattern recognition technology, the neural network does not need to give the empirical knowledge and discriminant function of the pattern in advance, and can automatically form the required decision-making area through its own learning mechanism. With more and more extensive applications, the most reported results in the literature mainly include the following: [0003] The standard Back Propagation Neural Network (BPNN) uses the fastest gradient descent static optimization method based on the error cost function for pattern recognition. Its fixed learning rate and paralysis of the learning process can easily lead to slow convergence and local minima. Value, network structure and scale are difficult to determine. The improved BPNN diagnosis method using variable lea...

AI Technical Summary

Problems solved by technology

Similar to RBFNN, the output layer of RBPNN still adopts the linear superposition of connection weights, and the sample "rejection" may occur

Images