TY - JFULL AU - H. El Fadili and K. Zenkouar and H. Qjidaa PY - 2007/12/ TI - Evolving Neural Networks using Moment Method for Handwritten Digit Recognition T2 - International Journal of Computer and Information Engineering SP - 3507 EP - 3511 VL - 1 SN - 1307-6892 UR - https://publications.waset.org/pdf/13943 PU - World Academy of Science, Engineering and Technology NX - Open Science Index 11, 2007 N2 - This paper proposes a neural network weights and topology optimization using genetic evolution and the backpropagation training algorithm. The proposed crossover and mutation operators aims to adapt the networks architectures and weights during the evolution process. Through a specific inheritance procedure, the weights are transmitted from the parents to their offsprings, which allows re-exploitation of the already trained networks and hence the acceleration of the global convergence of the algorithm. In the preprocessing phase, a new feature extraction method is proposed based on Legendre moments with the Maximum entropy principle MEP as a selection criterion. This allows a global search space reduction in the design of the networks. The proposed method has been applied and tested on the well known MNIST database of handwritten digits. ER -