Associative memory neural networks with concatenated vectors and nonzero diagonal terms
β Scribed by Emanuel Marom
- Publisher
- Elsevier Science
- Year
- 1990
- Tongue
- English
- Weight
- 498 KB
- Volume
- 3
- Category
- Article
- ISSN
- 0893-6080
No coin nor oath required. For personal study only.
β¦ Synopsis
The efJects oJ vector concatenation as well as that of eliminating the zero diagonal restriction of associative memory neural network matrices is anah, zed. Extensive computer simulations seem to indicate that the t~e of concatenated vectors increases the storage capaci O' of the association matrices, beyond the accepted practical limit Of 1). 14N, N being the length of the stored vector,s.
π SIMILAR VOLUMES
## Abstract In this paper, without assuming the boundedness, monotonicity and differentiability of the activation functions, we present new conditions ensuring existence, uniqueness, and global asymptotical stability of the equilibrium point of bidirectional associative memory neural networks with