A GEOMETRICAL LEARNING ALGORITHM OF BINARY NEURAL NETWORKS FOR CLASSIFICATION
二进制神经网络分类问题的几何学习算法

Binary to binary mapping for classification plays an important role in the researches on feed-forward-neural-network learning. In this paper, the geometrical method is employed to work out a new algorithm to train binary neural networks for classification. By analysis of every training vertex's geometrical location, the algorithm always produces a neural network of four layers for a certain classification problem. The advantages of this algorithm are: it runs with guaranteed convergence and goes to converge much more quickly than BP and some other algorithms; it can determine the structure of the neural networks by learning so that a precise classification is carried out.In addition, every neuron generated by the algorithm employs a hard-limit activation function with integer synaptic weights, which makes the actual implementation by VLSI technology more facilitated.