Characteristics of small scale nonmonotonic neuron networks having large potentiality for learning

We report a study on learning ability of a deterministic Boltzmann machine (DBM) with neurons which have a nonmonotonic activation function. We use an end-cut-off-type function with a threshold parameter `θ´ as the nonmonotonic function. Numerical simulations of nonlinear problems, such as the 2-parity problem and the 4-parity problem, show that the DBM network with nonmonotonic neurons has higher learning ability compared to the network with monotonic neurons