Title :
Improving the capacity of complex-valued neural networks with a modified gradient descent learning rule
Author_Institution :
Dept. of Electron. Eng., Ta-Hwa Inst. of Technol., Hsin-Chu, Taiwan
fDate :
3/1/2001 12:00:00 AM
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;
Journal_Title :
Neural Networks, IEEE Transactions on
