Abstract
The effects of vector concatenation as well as that of eliminating the zero diagonal restriction of associative memory neural network matrices is analyzed. Extensive computer simulations seem to indicate that the use of concatenated vectors increases the storage capacity of the association matrices, beyond the accepted practical limit of 0.14N, N being the length of the stored vectors.
Original language | English |
---|---|
Pages (from-to) | 311-318 |
Number of pages | 8 |
Journal | Neural Networks |
Volume | 3 |
Issue number | 3 |
DOIs | |
State | Published - 1990 |
Keywords
- Associative memories
- Error correction
- Memory capacity
- Neural networks
- Nonzero diagonal matrix
- Vector concatenation