Evolving neural network based on improved genetic algorithm for pattern classification
Chen Guang Guo · Journal of Dalian Maritime University · 2009
An evolving neural network classifier using variable string genetic algorithm(VGA) was developed to study pattern classification for image and speech.The classifier could automatically evolve the appropriate architecture of neural network and find a near-optimal set of connection weights globally.Then the conformable connection weights for pattern classification could be found with backpropagation(BP) algorithm.Simulations on vowel data and SPOT multi-spectral image data show that the VGA-BP classifier has higher classification precision comparing with Bayes classifier and k-NN classifier in pattern classification.