A novel chaotic hetero-associative memory

In this study, a novel hetero-associative memory with dynamic behavior is proposed. The proposed hetero-associative memory can store as twice as a regular hetero-associative memory using a new extension of sparse learning method. The new learning method gives the network ability of successive learning, therefore it can store new patterns even after learning phase. In other words, learning step and recall step are not separated in this method. We also add chaos searching in recall step in order to make the network be able to converge into the best possible solution among whole search space. Chaotic behavior helps the network jumps from local minimums. Simulation result shows higher storage capacity and also better recall performance in comparison with regular hetero-associative memory with the presence of noisy input data.

[1]  E. Oja,et al.  Fast adaptive formation of orthogonalizing filters and associative memory in recurrent networks of neuron-like elements , 1976, Biological Cybernetics.

[2]  Ju-Jang Lee.  Dynamic bidirectional associative memory using chaotic neurons , 2006, Artificial Life and Robotics.

[3]  Masafumi Hagiwara,et al.  Chaotic bidirectional associative memory , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[4]  Masafumi Hagiwara,et al.  Successive learning in chaotic neural network , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[5]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1993 .

[6]  Peter Sussner,et al.  Morphological bidirectional associative memories , 1999, Neural Networks.

[7]  Aluizio F. R. Araújo,et al.  Controlling Chaos in Chaotic Bidirectional Associative Memories , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[8]  Bogdan Raducanu,et al.  Morphological Scale Spaces and Associative Morphological Memories: Results on Robustness and Practical Applications , 2004, Journal of Mathematical Imaging and Vision.

[9]  Kazuyuki Aihara,et al.  Threshold control of chaotic neural network , 2008, Neural Networks.

[10]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[11]  Xianglong Tang,et al.  A new parameter control method for S-GCM , 2005, Pattern Recognit. Lett..

[12]  J. Hopfield,et al.  Modeling the olfactory bulb and its neural oscillatory processings , 1989, Biological Cybernetics.

[13]  Toshihiro Arai,et al.  Hetero Chaotic Associative Memory for Successive Learning with Give Up Function -One-to-Many Associations , 2006, Artificial Intelligence and Applications.

[14]  Yuko Osana,et al.  Hetero Chaotic Associative Memory for Successive Learning with Multi-Winners Competition , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[15]  K. Aihara,et al.  Chaotic neural networks , 1990 .

[16]  Paul D. Gader,et al.  Fixed Points of Lattice Transforms and Lattice Associative Memories , 2006 .

[17]  Peter Sussner,et al.  Morphological associative memories , 1998, IEEE Trans. Neural Networks.

[18]  Zhijie Wang,et al.  Dynamic depression control of chaotic neural networks for associative memory , 2010, Neurocomputing.

[19]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[20]  Tao Wang,et al.  A novel GCM chaotic neural network for information processing , 2012 .

[21]  Kazuyuki Aihara,et al.  Associative memory with a controlled chaotic neural network , 2008, Neurocomputing.

[22]  Shin Ishii,et al.  A network of chaotic elements for information processing , 1996, Neural Networks.

[23]  Masafumi Hagiwara,et al.  Successive Learning in Hetero-Associative Memory Using Chaotic Neural Networks , 1999, Int. J. Neural Syst..

[24]  W. Freeman,et al.  How brains make chaos in order to make sense of the world , 1987, Behavioral and Brain Sciences.

[25]  Yong Yao,et al.  Model of biological pattern recognition with spatially chaotic dynamics , 1990, Neural Networks.