Title :
The associative memory with optimal storage error-correcting performance
Author :
Daming, Zhu ; Mingyan, Jiang ; Shaohan, Ma
Author_Institution :
Dept. of Comput. Sci., Shandong Univ., Jinan, China
Abstract :
The character of the associative memory is discussed emphatically from the viewpoint of the storage capacity and the associative ability of the network. The associative memory function can all be realized by utilizing the feedback network or the forward-feed network. The new algorithm, based on adaptive competing-classifying (ACC) algorithm, is presented here. Compared with other associative memories, the neural network determined by the algorithm has high error-correcting capability, large storage capacity, no “rejected-point” and no spurious attractive center. ACC algorithm can decrease the competition-number more than CC algorithm. The obtained network has the very strong ability of correcting errors and exceeds the storage capacity of HAM and BP networks
Keywords :
content-addressable storage; error correction; feedforward neural nets; optimisation; pattern classification; recurrent neural nets; unsupervised learning; ACC algorithm; adaptive competing-classifying algorithm; associative memory; error-correcting capability; feedback neural network; feedforward neural network; forward-feed neural network; optimal storage error-correcting performance; spurious attractive center; storage capacity; Associative memory; Computer errors; Computer science; Electronic mail; Joining processes; Linear approximation; Neural networks; Neurofeedback; Neurons; Stability;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.893401
