2nd generation neural networks /956 多层感知机(Multi--layer Perceptron,MLP) ■ 超过1层的hidden layers(正确输出未知的层) ▣BP算法[Rumelhart et al..,1986] ■Compute error signal Then,back-propagate error signal to get derivatives for learning X1 y1 X2 y2 X3 David E.Rumelhart,,Geoffrey E.Hinton,and Ronald J.Williams.(Oct.1986)."Learning reproontation-电yea6 ingors.Nature323(608笔斜大学研究生《模式识别》电子科技大学研究生《模式识别》 2nd Generation Neural Networks o 多层感知机(Multi-layer Perceptron, MLP) n 超过1层的hidden layers（正确输出未知的层） o BP算法 [Rumelhart et al., 1986] n Compute error signal; n Then, back-propagate error signal to get derivatives for learning 10 David E. Rumelhart,, Geoffrey E. Hinton, and Ronald J. Williams. (Oct.1986). "Learning representations by back-propagating errors". Nature 323 (6088): 533–536