Binary Neurons hard threshold 1.2output Stimulus Response 0.8 on 4=∑wx y=f(ue1+4,) 0.6 0.2 input 020 10 “Hard”threshold 411 -heaviside z≥日→ON ōff f()= 12 ese→OFF O=threshold ex:Perceptrons,Hopfield NNs,Boltzmann Machines Main drawbacks:can only map binary functions, biologically implausible. 09/07/2023 Artificial Neural Networks-I 1109/07/2023 Artificial Neural Networks - I 11 Binary Neurons ( )               = else OFF z ON f z “Hard” threshold = threshold hard threshold -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 heaviside • ex: Perceptrons, Hopfield NNs, Boltzmann Machines • Main drawbacks: can only map binary functions, biologically implausible. off on =  j i ij j u w x Stimulus ( ) i urest ui y = f + Response