The neural networks: application and optimization Application of Levenberg- Marquardt algorithm for Tifinagh character recognition

Levenberg-Marquardt (LM) Optimization is a virtual standard in nonlinear optimization. It is a pseudosecond order method which means that it works with only function evaluations and gradient information but it estimates the Hessian matrix using the sum of outer products of the gradients. In this word, we will applythe Levenberg- Marquardt method for learning and recognition pattern concerned Tifinaghcharacters; this last will be compared to other methods such as Windrow-Hoff (WH). This note reviews the application for Levenberg-Marquardt for network neuronal and also details the algorithm.