Complex-Valued Associative Memories with Projection and Iterative Learning Rules

Isokawa, Teijiro; Yamamoto, Hiroki; Nishimura, Haruhiko; Yumoto, Takayuki; Kamiura, Naotake; Matsui, Nobuyuki

doi:10.1515/jaiscr-2018-0015

Abstract

In this paper, we investigate the stability of patterns embedded as the associative memory distributed on the complex-valued Hopfield neural network, in which the neuron states are encoded by the phase values on a unit circle of complex plane. As learning schemes for embedding patterns onto the network, projection rule and iterative learning rule are formally expanded to the complex-valued case. The retrieval of patterns embedded by iterative learning rule is demonstrated and the stability for embedded patterns is quantitatively investigated.

References

[1] A. Hirose, editor, Complex-Valued Neural Networks: Theories and Application, volume 5 of Innovative Intelligence, World Scientific Publishing, Singapore, 2003.10.1142/9789812791184_0001
Search in Google Scholar Back to article
[2] T. Nitta, editor, Complex-Valued Neural Networks: Utilizing High-Dimensional Parameters, Information Science Reference, Hershey, New York, 2009.10.4018/978-1-60566-214-5
Search in Google Scholar Back to article
[3] A. Hirose, editor, Complex-Valued Neural Networks: Advances and Applications, The IEEE Press Series on Computational Intelligence, Wiley-IEEE Press, 2013.
Search in Google Scholar Back to article
[4] Y. Nakano and A. Hirose, Improvement of Plastic Landmine Visualization Performance by Use of Ring-CSOM and Frequency-Domain Local Correlation, IEICE Transactions, 92-C(1), pp.102–108, 2009.10.1587/transele.E92.C.102
Search in Google Scholar Back to article
[5] Rajoo Pandey, Complex-Valued Neural Networks for Blind Equalization of Time-Varying Channels, International Journal of Signal Processing, 1(1), pp.1–8, 2004.
Search in Google Scholar Back to article
[6] A. J. Noest, Associative Memory in Sparse Neural Networks, Europhysics Letters, 6(6), pp.469–474, 1988.10.1209/0295-5075/6/5/016
Search in Google Scholar Back to article
[7] N. N. Aizenberg and I. N. Aizenberg, CNN Based on Multi-Valued Neuron as a Model of Associative Memory for Gray-Scale Images, Proceedings of the 2nd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-92), pp.36–41, 1992.
Search in Google Scholar Back to article
[8] I. N. Aizenberg, N. N. Aizenberg, and J. Vandewalle, Multi-Valued and Universal Binary Neurons – Theory, Learning and Applications –, Kluwer Academic Publishers, Boston/Dordrecht/London, 2000.10.1007/978-1-4757-3115-6
Search in Google Scholar Back to article
[9] S. Jankowski, A. Lozowski, and J. M. Zurada, Complex-Valued Multistate Neural Associative Memory, IEEE Transactions on Neural Networks, 7(6), pp.1491–1496, 1996.10.1109/72.54817618263542
Open DOI Search in Google Scholar Back to article
[10] T. Isokawa, H. Nishimura, and N. Matsui, An Iterative Learning Scheme for Multistate Complex-Valued and Quaternionic Hopfield Neural Networks, Proceedings of International Joint Conference on Neural Networks (IJCNN2009), pp.1365–1371, 2009.
Search in Google Scholar Back to article
[11] M. K. Müezzinoğlu, C. Güzeliş, and J. M. Zurada, A New Design Method for the Complex-Valued Multistate Hopfield Associative Memory, IEEE Transactions on Neural Networks, 14(4), pp.891–899, 2003.10.1109/TNN.2003.81384418238068
Open DOI Search in Google Scholar Back to article
[12] D.-L. Lee, Improvements of complex-valued Hopfield associative memory by using generalized projection rules, IEEE Transaction on Neural Networks, 17(5), pp.1341–1347, 2006.
Search in Google Scholar Back to article
[13] M. Kobayashi, Pseudo-relaxation learning algorithm for complex-valued associative memory, International Journal of Neural Systems, 18(2), pp.147–156, 2008.10.1142/S012906570800145218452248
Open DOI Search in Google Scholar Back to article
[14] T. Kohonen, Self-Organization and Associative Memory, Springer, Berlin, Heidelberg, 1984.
Search in Google Scholar Back to article
[15] L. Personnaz, I. Guyon, and G. Dreyfus, Collective Computational Properties of Neural Networks: New Learning Mechanisms, Physical Review A, 34, pp.4217–4228, 1986.
Search in Google Scholar Back to article
[16] S. Diederich and M. Opper, Learning of Correlated Patterns in Spin-Glass Networks by Local Learning Rules, Physical Review Letters, 58, pp.949–952, 1987.10.1103/PhysRevLett.58.94910035080
Open DOI Search in Google Scholar Back to article
[17] H. Yamamoto, T. Isokawa, H. Nishimura, N. Kamiura, and N.Matsui, Pattern Stability on Complex-Valued Associative Memory by Local Iterative Learning Scheme, Proceedings of 6th International Conference on Soft Computing and Intelligent Systems & 13th International Symposium on Advanced Intelligent Systems (SCIS-ISIS 2012), pp.39–42, 2012.10.1109/SCIS-ISIS.2012.6505125
Search in Google Scholar Back to article
[18] F. Flueret and D. Geman, Stationary Features and Cat Detection, Journal of Machine Learning Research, 9, pp.2549–2578, 2008.
Search in Google Scholar Back to article
[19] T. Isokawa, H. Nishimura, A. Saitoh, N. Kamiura, and N. Matsui, On the Scheme of Quaternionic Multistate Hopfield Neural Network, Proceedings of Joint 4th International Conference on Soft Computing and Intelligent Systems and 9th International Symposium on advanced Intelligent Systems (SCIS & ISIS 2008), pp.809–813, 2008.
Search in Google Scholar Back to article
[20] T. Isokawa, H. Nishimura, and N. Matsui, Commutative Quaternion and Multistate Hopfield Neural Networks, Proceedings of IEEE World Congress on Computational Intelligence (WCCI2010), pp.1281–1286, 2010.
Search in Google Scholar Back to article
[21] T. Minemoto, T. Isokawa, H. Nishimura, and N. Matsui, Quaternionic multistate Hopfield neural network with extended projection rule, Artificial Life and Robotics, 21(1), pp.106–111, 2016.10.1007/s10015-015-0247-4
Open DOI Search in Google Scholar Back to article

Complex-Valued Associative Memories with Projection and Iterative Learning Rules

Abstract

Paradigm

My account