Analog Neurons sigmoid 12 output Stimulus Response 4= ∑wx y=f(u,e1+4） 04 input .10 6 8 10 8 2/(1+exp(-x)-1 “Soft”threshold 1 off f)= 2-1 -1.2 1+e: .ex:MLPs,Recurrent NNs,RBF NNs... Main drawbacks:difficult to process time patterns,biologically implausible. 09/07/2023 Artificial Neural Networks-I 1209/07/2023 Artificial Neural Networks - I 12 Analog Neurons ( ) 1 1 2 − + = −z e f z “Soft” threshold sigmoid -1.2 -1 -0.8 -0.6 -0.4 -0.2 0 0.2 0.4 0.6 0.8 1 1.2 -10 -8 -6 -4 -2 0 2 4 6 8 10 input output 2/(1+exp(-x))-1 • ex: MLPs, Recurrent NNs, RBF NNs... •Main drawbacks: difficult to process time patterns, biologically implausible. off on =  j i ij j u w x Stimulus ( ) i urest ui y = f + Response