Title :
A low-bit learning algorithm for digital multilayer neural networks applied to pattern recognition
Author :
Nakayama, Kenji ; KATAYAMA, Hiroshi
Author_Institution :
Dept. of Electr. & Comput. Eng., Kanazawa Univ., Japan
Abstract :
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
Keywords :
learning systems; neural nets; pattern recognition; digital multilayer neural networks; low-bit learning algorithm; pattern recognition; training; Hamming distance; Hysteresis; Logistics; Multi-layer neural network; Neural networks; Pattern recognition;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170632
