Inclined planes optimization algorithm in optimal architecture of MLP neural networks

In this paper an Inclined Planes Optimization algorithm, is used to optimize the performance of the multilayer perceptron. Indeed, the performance of the neural network depends on its parameters such as the number of neurons in the hidden layer and the connection weights. So far, most research has been done in the field of training the neural network. In this paper, a new algorithm optimization is presented in optimal architecture for data classification. Neural network training is done by backpropagation (BP) algorithm and optimization the architecture of neural network is considered as independent variables in the algorithm. The results in three classification problems have shown that a neural network resulting from these methods have low complexity and high accuracy when compared with results of Particle Swarm Optimization and Gravitational Search Algorithm.