N-bit Parity Neural Networks with minimum number of threshold neurons

Abstract

In this paper ordered neural networks for the Nbit parity function containing [log2(N + 1)] threshold elements are constructed. The minimality of this network is proved. The connection between minimum perceptrons of Gamb for the N-bit parity function and one combinatorial problems is established.

Keywords

• neural networks
• XOR problem
• perceptrons ofGamb