Quaternion-Valued Twin-Multistate Hopfield Neural Networks With Dual Connections

Dual connections (DCs) utilize the noncommutativity of quaternions and improve the noise tolerance of quaternion Hopfield neural networks (QHNNs). In this article, we introduce DCs to twin-multistate QHNNs. We conduct computer simulations to investigate the noise tolerance. The QHNNs with DCs were weak against an increase in the number of training patterns, but they were robust against increased resolution factor. The simulation results can be explained from the standpoints of storage capacities and rotational invariance.

[1]  Gouhei Tanaka,et al.  Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction , 2009, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[2]  Masaki Kobayashi,et al.  Quaternionic Hopfield neural networks with twin-multistate activation function , 2017, Neurocomputing.

[3]  H. Aoki.  A complex-valued neuron to transform gray level images to phase information , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[4]  Masaki Kobayashi,et al.  Hyperbolic Hopfield neural networks with directional multistate activation function , 2018, Neurocomputing.

[5]  Marcos Eduardo Valle,et al.  Complex-Valued Recurrent Correlation Neural Networks , 2014, IEEE Transactions on Neural Networks and Learning Systems.

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

[7]  T. Nitta.  An Extension of the Back-propagation Algorithm to Quaternions , 1996 .

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

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

[10]  Jacek M. Zurada,et al.  A new design method for the complex-valued multistate Hopfield associative memory , 2003, IEEE Trans. Neural Networks.

[11]  Masaki Kobayashi,et al.  Attractors accompanied with a training pattern of multivalued hopfield neural networks , 2015 .

[12]  Nobuyuki Matsui,et al.  An iterative learning scheme for multistate complex-valued and quaternionic Hopfield neural networks , 2009, 2009 International Joint Conference on Neural Networks.

[13]  Marcos Eduardo Valle,et al.  On the Dynamics of Hopfield Neural Networks on Unit Quaternions , 2018, IEEE Transactions on Neural Networks and Learning Systems.

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

[15]  Marcos Eduardo Valle,et al.  Continuous-Valued Quaternionic Hopfield Neural Network for Image Retrieval: A Color Space Study , 2017, 2017 Brazilian Conference on Intelligent Systems (BRACIS).

[16]  André J. Noest,et al.  Phasor Neural Networks , 1987, NIPS.

[17]  D.-L. Lee,et al.  Improvements of Complex-Valued Hopfield Associative Memory by Using Generalized Projection Rules , 2006, IEEE Transactions on Neural Networks.

[18]  Nobuyuki Matsui,et al.  Quaternionic multistate Hopfield neural network with extended projection rule , 2016, Artificial Life and Robotics.

[19]  Masaki Kobayashi,et al.  Storage capacity of rotor Hopfield neural networks , 2018, Neurocomputing.

[20]  Yasuaki Kuroe,et al.  Models of Hopfield-Type Clifford Neural Networks and Their Energy Functions - Hyperbolic and Dual Valued Networks - , 2011, ICONIP.

[21]  Nobuyuki Matsui,et al.  Pattern Retrieval by Quaternionic Associative Memory with Dual Connections , 2016, ICONIP.

[22]  Masaki Kobayashi,et al.  Twin-multistate commutative quaternion Hopfield neural networks , 2018, Neurocomputing.

[23]  Masaki Kobayashi,et al.  Pseudomemories of two‐dimensional multistate hopfield neural networks , 2017 .

[24]  Jacek M. Zurada,et al.  Stability condition for discrete time multi-valued recurrent neural networks in asynchronous update mode , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[25]  Yasuaki Kuroe,et al.  Models of hopfield-type quaternion neural networks and their energy functions , 2005, Int. J. Neural Syst..

[26]  Marcos Eduardo Valle,et al.  Theoretical and computational aspects of quaternionic multivalued Hopfield neural networks , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[27]  Masaki Kobayashi.  Gradient descent learning rule for complex‐valued associative memories with large constant terms , 2016 .

[28]  Pengsheng Zheng.  Threshold Complex-Valued Neural Associative Memory , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Naotake Kamiura,et al.  On the Scheme of Quaternionic Multistate Hopfield Neural Network , 2008 .

[30]  Masaki Kobayashi,et al.  Projection Rule for Rotor Hopfield Neural Networks , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[31]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[32]  Naotake Kamiura,et al.  Complex-Valued Associative Memories with Projection and Iterative Learning Rules , 2018, J. Artif. Intell. Soft Comput. Res..

[33]  D. A. Pospelov,et al.  Multivalued threshold functions , 1973 .

[34]  Masaki Kobayashi,et al.  Stability of Rotor Hopfield Neural Networks With Synchronous Mode , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[35]  Masaki Kobayashi.  Decomposition of Rotor Hopfield Neural Networks Using Complex Numbers , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[36]  Nobuyuki Matsui,et al.  Commutative quaternion and multistate Hopfield neural networks , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).