N-bit parity neural networks with minimum number of threshold neurons

M. Z. Arslanov

Institute of information and computation technologies Almaty 050010, Pushkin str.125, Kazakhstan

Abstract: In this paper ordered neural networks for the $N$-bit parity function containing $\mathop{\log }\nolimits_{2} (N+1)$ threshold elements are constructed. The minimality of this network is proved. The connection of minimum perceptrons of Gamb for the $N$-bit parity function wint one combinatorial problems is established.

Keywords: Neural Networks, XOR problem, Perceptrons of Gamb.

MSC: 05XX

Received: 08.06.2016

Language: English