1. Synthesization of high-capacity auto-associative memories using complex-valued neural networks
- Author
-
Haixia Long, Yu-Jiao Huang, Xiao-Yan Wang, and Xu-Hua Yang
- Subjects
Physical neural network ,0209 industrial biotechnology ,Quantitative Biology::Neurons and Cognition ,Artificial neural network ,Computer science ,business.industry ,Time delay neural network ,Activation function ,General Physics and Astronomy ,02 engineering and technology ,Autoassociative memory ,020901 industrial engineering & automation ,Cellular neural network ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,Types of artificial neural networks ,business ,Stochastic neural network - Abstract
In this paper, a novel design procedure is proposed for synthesizing high-capacity auto-associative memories based on complex-valued neural networks with real-imaginary-type activation functions and constant delays. Stability criteria dependent on external inputs of neural networks are derived. The designed networks can retrieve the stored patterns by external inputs rather than initial conditions. The derivation can memorize the desired patterns with lower-dimensional neural networks than real-valued neural networks, and eliminate spurious equilibria of complex-valued neural networks. One numerical example is provided to show the effectiveness and superiority of the presented results.
- Published
- 2016
- Full Text
- View/download PDF