Decomposition of Rotor Hopfield Neural Networks Using Complex Numbers

A complex-valued Hopfield neural network (CHNN) is a multistate model of a Hopfield neural network. It has the disadvantage of low noise tolerance. Meanwhile, a symmetric CHNN (SCHNN) is a modification of a CHNN that improves noise tolerance. Furthermore, a rotor Hopfield neural network (RHNN) is an extension of a CHNN. It has twice the storage capacity of CHNNs and SCHNNs, and much better noise tolerance than CHNNs, although it requires twice many connection parameters. In this brief, we investigate the relations between CHNN, SCHNN, and RHNN; an RHNN is uniquely decomposed into a CHNN and SCHNN. In addition, the Hebbian learning rule for RHNNs is decomposed into those for CHNNs and SCHNNs.

[1]  Danilo P. Mandic,et al.  Performance Bounds of Quaternion Estimators , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Nobuyuki Matsui,et al.  On the fundamental properties of fully quaternionic hopfield network , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[3]  Masaki Kobayashi,et al.  Complex-Valued Bipartite Auto-Associative Memory , 2014, IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences.

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

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

[6]  Masaki Kobayashi,et al.  Hybrid Quaternionic Hopfield Neural Network , 2015, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[7]  Masaki Kobayashi,et al.  Symmetric Complex-Valued Hopfield Neural Networks , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[8]  J Cook,et al.  The mean-field theory of a Q-state neural network model , 1989 .

[9]  Masaki Kobayashi.  Information geometry of rotor Boltzmann machines , 2016 .

[10]  Akira Hirose,et al.  Complex-Valued Neural Networks , 2006, Studies in Computational Intelligence.

[11]  Masaki Kobayashi,et al.  Chaotic Rotor Associative Memory , 2009 .

[12]  Masaki Kobayashi,et al.  Fundamental Abilities of Rotor Associative Memory , 2010, 2010 IEEE/ACIS 9th International Conference on Computer and Information Science.

[13]  Pascal Chevalier,et al.  Widely linear estimation with complex data , 1995, IEEE Trans. Signal Process..

[14]  Akira Hirose,et al.  Complex-Valued Neural Networks: Advances and Applications , 2013 .

[15]  Robert Schober,et al.  Receivers with widely linear processing for frequency-selective channels , 2003, IEEE Trans. Commun..

[16]  Akira Hirose,et al.  Complex-Valued Neural Networks: Theories and Applications , 2003 .

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

[18]  Jonas Schreiber.  Complex Valued Neural Networks Utilizing High Dimensional Parameters , 2016 .

[19]  Masaki Kobayashi,et al.  Rotor Associative Memory with a Periodic Activation Function , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[20]  K. Aihara,et al.  Complex-Valued Multistate Associative Memory With Nonlinear Multilevel Functions for Gray-Level Image Reconstruction , 2009, IEEE Transactions on Neural Networks.

[21]  Nobuyuki Matsui,et al.  On the performance of Quaternionic Bidirectional Auto-Associative Memory , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[22]  Lutz H.-J. Lampe,et al.  Data-aided and blind stochastic gradient algorithms for widely linear MMSE MAI suppression for DS-CDMA , 2004, IEEE Transactions on Signal Processing.

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

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

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

[26]  Masaki Kobayashi,et al.  Hyperbolic Hopfield Neural Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Masaki Kobayashi,et al.  Rotational invariance of quaternionic hopfield neural networks , 2016 .

[28]  Munakata,et al.  Neural-network model composed of multidimensional spin neurons. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[29]  D. Mandic,et al.  Complex Valued Nonlinear Adaptive Filters: Noncircularity, Widely Linear and Neural Models , 2009 .