The Evolutionary Algorithms have been used for neural networks in two main ways: (i) to optimize the network architecture in terms of hidden layers and number of neurons in each layers, and (ii) to train the weights of fixed architecture. While most previous work focuses on only one of these two options, this paper investigative Evolutionary approach called Breeder Genetic Programming (BGP) in which the architecture and the weights are optimized simultaneously. The genotype of each network is represented as a tree whose depth and width are dynamically adapted to the particular application by specifically defined genetic operators. The weights are trained by Gaussian approximation. The fitness function has been chosen as a function increasing when the mean square error at the end of the training and the number of epochs needed for learning are increase. In this paper, I have fined optimal Bayesian neural network using Breeder genetic programming to classify or identify acoustic radar Patterns. The results demonstrate that the method is capable of successfully identifying the different acoustic radar patterns