Title :
A new architecture of neural network
Author :
Zhang, Yongjun ; Chen, Zongzhi
Author_Institution :
Inst. of Electron., Acad. Sinica, Beijing, China
Abstract :
Describes a novel neural-network architecture, the neural network loop (NNL), and its learning rules. It can operate as Hopfield, BAM (bidirectional associative memory), and other kinds of neural networks. In particular, it can perform multiple category associative memory. This capability is very similar to that of the human brain. It can be applied to pattern recognition and associative memory. Computer simulation was carried out, and the results prove that NNL is an effective network
Keywords :
content-addressable storage; learning systems; neural nets; pattern recognition; Hopfield; NNL; architecture; bidirectional associative memory; learning rules; multiple category associative memory; neural network; neural network loop; pattern recognition; Associative memory; Biological neural networks; Brain modeling; Computer simulation; Humans; Nervous system; Neural networks; Neurons; Pattern recognition;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170504
