Improving the capacity of complex-valued neural networks with a modified gradient descent learning rule

Author

Lee, Donq Liang

Author_Institution

Dept. of Electron. Eng., Ta-Hwa Inst. of Technol., Hsin-Chu, Taiwan

Volume

12

Issue

2

fYear

2001

fDate

3/1/2001 12:00:00 AM

Firstpage

439

Lastpage

443

Abstract

Jankowski et al. proposed (1996) a complex-valued neural network (CVNN) which is capable of storing and recalling gray-scale images. The convergence property of the CVNN has also been proven by means of the energy function approach. However, the memory capacity of the CVNN is very low because they use a generalized Hebb rule to construct the connection matrix. In this letter, a modified gradient descent learning rule (MGDR) is proposed to enhance the capacity of the CVNN. The proposed technique is derived by applying gradient search over a complex error surface. Simulation shows that the capacity of CVNN with MGDR is greatly improved

Keywords

Hebbian learning; content-addressable storage; gradient methods; image retrieval; neural nets; search problems; CVNN; MGDR; complex error surface; complex-valued neural networks; connection matrix; convergence; energy function; generalized Hebb rule; gradient search; gray-scale image recall; gray-scale image storage; modified gradient descent learning rule; Associative memory; Convergence; Councils; Data engineering; Gray-scale; Neural networks; Neurons; Prototypes; Quantization; Very large scale integration;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.914540

Filename

914540