Empirical determination of optimal configuration for characteristics of a multilayer perceptron neural network in nonlinear regression

In this paper, we determine an optimal configuration for characteristics of a multilayer perceptron neural network (MPL) in nonlinear regression for predicting crop yield. Monte Carlo simulation approach has been used to train several databases generated by varying the internal structure of 3-MLP from simple to complex for five (5) different algorithms most commonly used. Results showed that the optimal configuration is obtained with the Levenberg Marquard algorithm, 75% of the number of input variables as number of hidden nodes, learning rate 40%, minimum sample size 150, tangent hyperbolic and exponential functions in the hidden and output layers respectively. This configuration has been illustrated with real life data.