Only One Neuron either N-bit Parity Rule Based Modified Translated Multiplicative or McCulloch-Pitts Models for Some Machine Learning Problems

Abstract

In this study, solutions to machine learning problems such as Monk’s 2 (M 2 ), Balloon and Tic-Tac-Toe problems employing a single neuron dependent on rules which use either modified translated multiplicative (π m ) neuron or McCulloch-Pitts neuron model is proposed. Since M 2 problem is similar to N-bit parity problem, translated multiplicative (π t ) neuron model is modified for M 2 problem. Also, McCulloch-Pitts neuron model is used to increase classification performance. Then either πm or McCulloch-Pitts neuron model is applied to Balloon and Tic-Tac-Toe problems. When the result of proposed only one π m neuron model that is not required any training stage and hidden layer is compared with the other approaches, it shows satisfactory performance.