微型机与应用
微型機與應用
미형궤여응용
MICROCOMPUTER & ITS APPLICATIONS
2012年
5期
69-70,74
,共3页
函数逼近%多项式神经网络%权值预确定%区间折半搜寻法
函數逼近%多項式神經網絡%權值預確定%區間摺半搜尋法
함수핍근%다항식신경망락%권치예학정%구간절반수심법
function approximation%polynomial neural network%weights pre-set%interval binary search method
以多项式函数作为神经元的激活函数，结合矩阵伪逆的思想预先确定网络权值，并利用区间折半搜寻法自动优化隐层神经元数。通过对Hermit函数的仿真，充分显示了综合优化神经网络算法对函数具有较好的逼近。
以多項式函數作為神經元的激活函數，結閤矩陣偽逆的思想預先確定網絡權值，併利用區間摺半搜尋法自動優化隱層神經元數。通過對Hermit函數的倣真，充分顯示瞭綜閤優化神經網絡算法對函數具有較好的逼近。
이다항식함수작위신경원적격활함수，결합구진위역적사상예선학정망락권치，병이용구간절반수심법자동우화은층신경원수。통과대Hermit함수적방진，충분현시료종합우화신경망락산법대함수구유교호적핍근。
This paper considerates polynomial function as neurons activation function and combines with the thought of pseudo inverse matrix, network weights are predetermined, and by using interval binary search method ,the hidden layer number of neurons are optimized by itself. Through the simulation of the Hermit function , it can be fully seen that the comprehensive of optimizing neural network algorithm has good approximation.
