Abstract | ||
---|---|---|
This paper presents an analysis of a random access memory (RAM)-based associative memory which uses a weighted voting scheme for information retrieval. This weighted voting memory can operate in heteroassociative or autoassociative mode, can store both real-valued and binary-valued patterns and, unlike memory models, is equipped with a rejection mechanism. A theoretical analysis of the performance of the weighted voting memory is given for the case of binary and random memory sets. Performance measures are derived as a function of the model parameters: pattern size, window size, and number of patterns in the memory set. It is shown that the weighted voting model has large capacity and error correction. The results show that the weighted voting model can successfully achieve high-detection and -identification rates and, simultaneously, low-false-acceptance rates. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/TNN.2007.891196 | IEEE Transactions on Neural Networks |
Keywords | DocType | Volume |
pattern size,neural network,random memory set,random-access storage,rejection mechanism,weighted voting,weighted voting scheme,weighted voting memory,memory set,information retrieval,random access memory,associative memory,retrieval,window size,low-false-acceptance rate,memory model,model parameter,voting,weighted voting model,content-addressable storage,capacity,computer simulation,memory,neural networks,information analysis,error correction,artificial intelligence,algorithms,biomimetics | Journal | 18 |
Issue | ISSN | Citations |
3 | 1045-9227 | 9 |
PageRank | References | Authors |
0.70 | 25 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaoyan Mu | 1 | 29 | 2.88 |
Paul Watta | 2 | 11 | 1.48 |
M. H. Hassoun | 3 | 92 | 13.12 |