This paper combines theory of wavelet analysis with conventional neural network . substituting wavelet function for sigmoid function in neural network , to form wavelet neural network 本文將小波分析理論與傳統(tǒng)神經(jīng)網(wǎng)絡理論相結合,用小波函數(shù)代替?zhèn)鹘y(tǒng)神經(jīng)網(wǎng)絡中的sigmoid函數(shù),構成小波神經(jīng)網(wǎng)絡。
Finally , bp neural network is improved for face recognition , the problem on choice of parameters is discussed , the sigmoid function and weight adjustment are improved for higher convergence speed 討論了傳統(tǒng)bp神經(jīng)網(wǎng)絡的參數(shù)選取問題,對sigmoid函數(shù)和網(wǎng)絡學習速率進行了改進,以提高系統(tǒng)的收斂速度和收斂率。