前馈神经网络改进算法及其在矿床预测中的应用

A Fast Learning Algorithm for Feedforward Neural Networks and Its Application in Deposit Forecasting

利用凸函数共轭性质中的Young不等式构造前馈神经网络优化目标函数,这个优化目标函数对于权值和隐层输出来说均为凸函数,不存在局部最小。此目标函数的优化速度快,大大提高了前馈神经网络的学习效率。把这种快速算法应用于矿床预测,取得了良好效果。

This paper presents a new algorithm for feedforward neural networks based on a new optimal target fun- ction constructed according to Young inequality in the conjugate of convex function. The optimal target function is a convex function to the weight values between neurons in different layers and outputs of hidden layers. The target function's optimal velocity is high, so it can boost learning efficiency of feedforward neural networks. The numerical experiments show that the new algorithm is very simple, can accelerate the convergence rate, strength the generalization capability and reduce the error. It achieves more effective results to apply the fast algorithm to deposit forecasting.