论文信息 - Noise Robust Gradient Descent Learning for Complex-Valued Associative Memory

Noise Robust Gradient Descent Learning for Complex-Valued Associative Memory

Complex-valued Associative Memory (CAM) is an advanced model of Hopfield Associative Memory. The CAM is based on multi-state neurons and has the high ability of representation. Lee proposed gradient descent learning for the CAM to improve the storage capacity. It is based on only the phases of input signals. In this paper, we propose another type of gradient descent learning based on both the phases and the amplitude. The proposed learning method improves the noise robustness and accelerates the learning speed.

Masaki Kobayashi | Michimasa Kitahara | Hirofumi Yamada

[1] Jacek M. Zurada,et al. Complex-valued multistate neural associative memory , 1996, IEEE Trans. Neural Networks.

[2] Noest. Discrete-state phasor neural networks. , 1988, Physical review. A, General physics.

[3] Wen-June Wang,et al. A multivalued bidirectional associative memory operating on a complex domain , 1998, Neural Networks.

[4] Donq-Liang Lee. Improving the capacity of complex-valued neural networks with a modified gradient descent learning rule , 2001, IEEE Trans. Neural Networks.

[5] J J Hopfield,et al. Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[6] H. Aoki. Image Association Using a Complex-Valued Associative Memory Model , 2000 .

[7] J J Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[8] Donq-Liang Lee. Complex-Valued Neural Associative Memories: Network Stability and Learning Algorithm , 2003 .

[9] J Cook,et al. The mean-field theory of a Q-state neural network model , 1989 .

[10] Yukio Kosugi,et al. An image storage system using complex-valued associative memories , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.