A low-bit learning algorithm for digital multilayer neural networks applied to pattern recognition

A new low-bit learning algorithm for digital multilayer neural networks applied to pattern recognition is proposed. The training can be carried out with a small number of bits. To make the neural network insensitive to noisy patterns, conditions to be satisfied by hidden layer outputs are discussed. Based on this, optimum targets are assigned to the hidden layers. Computer simulation demonstrated the efficiency of the proposed method. >