Pattern Retrieval by Quaternionic Associative Memory with Dual Connections
An associative memory based on Hopfield-type neural network, called Quaternionic Hopfield Associative Memory with Dual Connection (QHAMDC), is presented and analyzed in this paper. The state of a neuron, input, output, and connection weights are encoded by quaternion, a class of hypercomplex number systems with non-commutativity for its multiplications. In QHAMDC, calculation for an internal state of a neuron is conducted by two types of multiplications for neuron’s output and connection weight. This makes robustness of the proposed associative memory for retrieval of patterns. The experimental results show that the performances of retrieving patterns by QHAMDC are superior to those by the previous QHAM.
This study was financially supported by Japan Society for the Promotion of Science (Grant-in-Aids for Scientific Research (C) 16K00337).
- 2.Aizenberg, N.N., Ivaskiv, Y.L., Pospelov, D.A.: About one generalization of the threshold function. Doklady Akademii Nauk SSSR (The Reports of the Academy of Sciences of the USSR) 196(6), 1287–1290 (1971)Google Scholar
- 4.Aizenberg, N.N., Aizenberg, I.N.: CNN based on multi-valued neuron as a model of associative memory for gray-scale images. In: Proceedings of the 2nd IEEE International Workshop on Cellular Neural Networks and their Applications, pp. 36–41 (1992)Google Scholar
- 9.Isokawa, T., Nishimura, H., Saitoh, A., Kamiura, N., Matsui, N.: On the scheme of quaternionic multistate Hopfield neural network. In: Proceedings of of Joint 4th International Conference on Soft Computing and Intelligent Systems and 9th International Symposium on advanced Intelligent Systems, pp. 809–813 (2008)Google Scholar
- 12.Minemoto, T., Isokawa, T., Matsui, N., Kobayashi, M., Nishimura, H.: On the performance of quaternionic bidirectional auto-associative memory. In: Proceedings of International Joint Conference on Neural Networks, #15594, 6 pages (2015)Google Scholar
- 14.Bülow, T.: Hypercomplex spectral signal representations for the processing and analysis of images. Ph.D. thesis, Christian-Albrechts-Universität zu Kiel (1999)Google Scholar
- 16.Isokawa, T., Nishimura, H., Matsui, N.: Quaternionic neural networks for associative memories. In: Hirose, A. (ed.) Complex-Valued Neural Networks: Advances and Applications, pp. 103–131. Wiley-IEEE Press (2013)Google Scholar