论文信息 - Investigation of recall image by Partitioned Hopfield Neural Network

Investigation of recall image by Partitioned Hopfield Neural Network

In this study, we propose Partitioned Hopfield Neural Network (PHNN) to realize the memory mechanism of the human brain. The PHNN is realized by arranging cell which has a small HNN in the whole image regularly without overlap. By computer simulations, we confirm that the PHNN recalls the whole image from the partial characteristic of the stored images.

Yoshifumi Nishio | Yoko Uwate | Chihiro Ikuta | Tomoya Shima

[1] B. K. Jenkins,et al. Image restoration using a neural network , 1988, IEEE Trans. Acoust. Speech Signal Process..

[2] G. Palm,et al. On associative memory , 2004, Biological Cybernetics.

[3] Mohamad H. Hassoun,et al. A two-level Hamming network for high performance associative memory , 2001, Neural Networks.

[4] Ling Guan,et al. A Partitioned Modified Hopfield Neural Network Algorithm for Real-Time Image Restoration , 1996, Real Time Imaging.

[5] Nasser M. Nasrabadi,et al. Object recognition using multilayer Hopfield neural network , 1997, IEEE Trans. Image Process..

[6] Mamoru Tanaka,et al. An image reconstruction system by neural network with median filter , 1993, 1993 IEEE International Symposium on Circuits and Systems.

[7] John J. Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities , 1999 .

[8] J. Austin. Associative memory , 1987 .

[9] Andreas Knoblauch,et al. Neural associative memory for brain modeling and information retrieval , 2005, Inf. Process. Lett..