DocumentCode :
2766079
Title :
Models of Self-Correlation Type Complex-Valued Associative Memories and Their Performance Comparison
Author :
Kuroe, Yasuaki ; Taniguchi, Yuriko
Author_Institution :
Kyoto Inst. of Technol., Kyoto
fYear :
0
fDate :
0-0 0
Firstpage :
213
Lastpage :
217
Abstract :
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 functions. In this paper, we propose two additional models using different nonlinear complex functions and investigate their behavior as associative memories theoretically. Comparisons are also made among these three models in terms of their performance: dynamics and storage capabilities.
Keywords :
content-addressable storage; neural nets; activation function; neural networks; nonlinear complex function; self-correlation type complex-valued associative memories; Artificial neural networks; Associative memory; Backpropagation; Feedforward neural networks; Information processing; Information science; Neural networks; Nonlinear dynamical systems; Orbits; Recurrent neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
Type :
conf
DOI :
10.1109/IJCNN.2006.246682
Filename :
1716093
Link To Document :
بازگشت