Neural Networks Algorithm Based on Factor Analysis

Shifei Ding, Weikuan Jia, Xinzheng Xu, Hong Zhu

Abstract: Aimming at the characteristics that the samples to be processed have high-dimension feature variables, and combining with the structure feature of neural networks, a new algorithm of Neural Networkss (NNs) based on Factor Analysis (FA) is proposed. Firstly we reduce the dimensionality of the feature space by FA, regard the data after dimension reduction as the input of the neural networks, and then output the prediction results after training and emulating. This algorithm can simplify the NNs structure, improve the velocity of convergence, and save the running time. Then we apply the new algorithm in the field of pest prediction to emulate. The results show that the prediction precision is not reduced, the error of the prediction value is reduced by using the algorithm here, and the algorithm is effective.