On-line learning in a discrete state space
Wolfgang Kinzel, Robert Urbanczik · Journal of Physics A Mathematical and General · 1998
On-line learning of a rule given by an N -dimensional Ising perceptron is considered for the case when the student is constrained to take values in a discrete state space of size . For L = 2 no on-line algorithm can achieve a finite overlap with the teacher in the thermodynamic limit. However, if L is on the order of , Hebbian learning does achieve a finite overlap.