Distinguishing features of a small Hopfield model with clipping of synapses

To estimate the memory storage as well as the operational reliability of a small Hopfield neural network model with clipping of synapses, the combinatorial methods have been applied. It has been demonstrated that the recognition error probability depends on parityoddness of etalons number, which causes reliability to decrease sawtooth-like rather than monotonously. It had been also shown that the reliability of the network based on odd number of the etalons can be increased by adding a random etalon.