In this paper, I present a novel hybrid face recognition approach based on a convolutional neural architecture, designed to robustly detect highly variable face patterns. With the weights of the trained neural networks there are created kernel window

In this paper we present the systematic trajectory search algorithm (STSA) which first globally explores the solution space then makes thorough local searches in promising areas. The STSA has been tested on training feedforward neural network

Introducing the rank-weight method into the basic ant colony optimization (ACO), we use the modified ACO to optimize the weights and thresholds value of neural networks (NN). And when the BPNN is being trained, this method can solve the disad

0A study on intrusion detection using neural networks trained with evolutionary algorithms