Abstract: Multilayer perceptrons of convolutional neural networks use the gradient descent algorithm for training，there are often problems of slow convergence and small localization． In order to solve the problem，we propose a method to calculate the optimal initialization weight by using information interaction to improve the proposed network structure，which can effectively reduce the training time and avoid the local minimum problem． Firstly we use mathematical theory to derive the formula for the optimal initialization weight of the ＲeLU function． We target 2-channel network structure using this method，directly substituting data to find the optimal initial weight．Through multiple training and testing of the three data sets，better results are obtained． Average matching accuracy for grayscale images is increased by about 1． 5%． For the FPＲ95，the average value also dropped from 5． 23 to 4． 65． Initialization weight setting prevents neurons from entering the hard saturated region． And it has the advantages of higher precision，stable effect and fast convergence．

Key words: neural network, weight, information interaction