Learning by dilution in a neural network
B López, Wolfgang Kinzel · Journal of Physics A Mathematical and General · 1997
A perceptron with N random weights can store of the order of N patterns by removing a fraction of the weights without changing their strengths. The critical storage capacity as a function of the concentration of the remaining bonds for random outputs and for outputs given by a teacher perceptron is calculated. A simple Hebb-like dilution algorithm is presented which, in the teacher case, reaches the optimal generalization ability.