Abstract | ||
---|---|---|
This letter presents a crosscorrelational associative memory model which realizes selective retrieval of pattern sequences. When hierarchically correlated sequences are memorized, sequences of the correlational centers can be defined as the concept sequences. The authors propose a modified neuro-window method which enables selective retrieval of memory sequences and concept sequences. It is also shown that the proposed model realizes capacity expansion of the memory which stores random sequences. |
Year | DOI | Venue |
---|---|---|
1999 | 10.1109/72.737505 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
selective retrieval,crosscorrelational associative memory model,memory sequence,concept sequence,capacity expansion,hierarchically correlated sequence,correlational center,modified neuro-window method,pattern sequence,random sequence,associative memory,learning artificial intelligence,intelligent networks,pattern recognition,sequences,autocorrelation | Content-addressable memory,Sequential logic,Pattern recognition,Computer science,Linear map,Artificial intelligence,Content-addressable storage,Covariance matrix,Artificial neural network,Eigenvalues and eigenvectors | Journal |
Volume | Issue | ISSN |
10 | 1 | 1045-9227 |
Citations | PageRank | References |
0 | 0.34 | 6 |
Authors | ||
2 |