ABSTRACT
This chapter explores the model of the three-inputthree-input Euler-polynomial neuronetEuler-polynomial neurone. Moreover, a so-called weights-and-structure-determination (WASD) algorithm has been developed to determine the optimal weights and structure of the established three-input Euler-polynomial neuronet. Based on the aforementioned theoretical basis, the three-inputthree-input Euler-polynomial neuronetEuler-polynomial neuronet is established. In view of the fact that the multi-input systems are also frequently encountered systems, it is worth further investigating the three-input neuronets. Numerical results further substantiate the superior performance of the three-input Euler-polynomial neuronet equipped with theWASD algorithm in terms of training, testing and prediction. More specifically, the WASD algorithm exploits the weights-direct-determination weights-direct-determination subalgorithm to determine the optimal weights between hidden-layer and output-layer neurons directly on one hand; and, on the other hand, it can obtain the optimal structure of the three-input Euler-polynomial neuronet during the training process. Multi-input artificial neuronetsartificial neuronets are simplified systems, which emulate the organization structures, signal processingsignal processing methods and system functions of biological neuronets.
