Models of Self-correlation Type Complex-Valued Associative Memories and Their Dynamics
Associative memories are one of the popular applications of neural networks and several studies on their extension to the complex domain have been done. One of the important factors to characterize behavior of a complex-valued neural network is its activation function which is a nonlinear complex function. We have already proposed a model of self-correlation type associative memories using complex-valued neural networks with one of the most commonly used activation function. In this paper, we propose two additional models using different nonlinear complex functions and investigated their behaviors as associative memories theoretically. Comparisons are also made among these three models in terms of dynamics and storage capabilities.
KeywordsEquilibrium Point Activation Function Nonlinear Dynamical System Associative Memory Hadamard Matrice
Unable to display preview. Download preview PDF.
- 2.Kuroe, Y., Hashimoto, N., Mori, T.: Qualitative analysis of a self-correlation type complex-valued associative memories. Nonlinear Analysis 47, 5795–5806 Google Scholar
- 4.Nemoto, I., Kono, T.: Complex-valued neural network. The Trans. of IEICE J74-D-II (9), 1282–1288 (1991) (in Japanese)Google Scholar
- 5.Noest, A.J.: Phaser neural network. In: Anderson, D.Z. (ed.) Neural Informaion Processing Systems, pp. 584–591. AIP, New York (1988)Google Scholar