Abstract
Neural associative memories are considered in which the elements of the weight matrix are taken to be stochastic variables. The probability density function of each weight is given by the solution of Schrödinger’s diffusion equation. The weights of the proposed associative memories are updated with the use of a learning algorithm that satisfies quantum mechanics postulates. This learning rule is proven to satisfy two basic postulates of quantum mechanics: (a) existence in superimposing states, (b) evolution between the superimposing states with the use of unitary operators. Taking the elements of the weight matrix of the associative memory to be stochastic variables means that the initial weight matrix can be decomposed into a superposition of associative memories. This is equivalent to mapping the fundamental memories (attractors) of the associative memory into the vector spaces which are spanned by the eigenvectors of the superimposing matrices and which are related to each other via unitary rotations. In this way, it can be shown that the storage capacity of the associative memories with stochastic weights increases exponentially with respect to the storage capacity of conventional associative memories.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
S. Aiyer, M. Niranjan, F. Fallside, Theoretical investigation into the performance of the Hopfield model. IEEE Trans. Neural Netw. 15(1), 204–215 (1990)
J.R. Chumbley, R.J. Dolan, K.J. Friston, Attractor models of working memory and their modulation by reward. Biol. Cybern. 98, 11–18 (2008)
G. Deco, E.T. Rolls, Attention, short-memory and action selection: a unifying theory. Prog. Neurobiol. 76, 236–256 (2005)
G. Deco, D. Marti, A. Ledberg, R. Reig, M.V. Sanchez Vives, Effective reduced diffusion-models: A data driven approach to the analysis of neuronal dynamics. PLoS Comput. Biol. 5(12), e1000587 (2009)
D. Dubois, L. Foulloy, G. Mauris and H. Prade, Probability-possibility transformations, triangular fuzzy sets and probabilistic inequalities. Reliab. Comput. 10(4), 273–297 (2004)
L.M. Harisson, K. David, K.J. Friston, Stochastic models of neuronal dynamics. Phil. Tran. R. Soc. B 360, 1075–1091 (2005)
S. Haykin, Neural Networks: A Comprehensive Foundation (McMillan, New York, 1994)
J.J. Hopfield, Neural networks as physical systems with emergent computational abilities. Proc. Natl. Acad. Sci. USA 79, 2444–2558 (1982)
S. Hu, X. Liao, X. Mao, Stochastic Hopfield neural networks. J. Phys. A Math. Gen. 35, 1–15 (2003)
Y. Katory, Y. Otsubo, M. Okada, K. Aihara, Stability analysis of associative memory network composed of stochastic neurons and dynamic synapses. Front. Comput. Neurosci. 7, 6 (2013)
B. Kosko, Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence (Prentice Hall, Englewood Cliffs, 1992)
M. Loh, E.T. Rolls, G. Deco, Statistical fluctuation in attractor networks related to Schizophrenia. Pharmacopsychiatry 40, 78–84 (2007)
M. Loh, E.T. Rolls, G. Deco, A dynamical systems hypothesis of Schizophrenia. PLoS Comput. Biol. 3(11), 1–11 (2007)
M. Mirrahimi, P. Rouchon, Controllability of quantum harmonic oscillators. IEEE Trans. Automat. Control. 45(5), 745–747 (2004)
M. Perus, H. Bischof, J. Caulfield, C.K. Loo, Quantum implementable selective reconstruction of high resolution images. Appl. Opt. 43, 6134–6138 (2004)
G.G. Rigatos, Quantum wave-packets in fuzzy automata and neural associative memories. Int. J. Mod. Phys. C 18(9), 1551 (2007)
G.G. Rigatos, Stochastic processes and neuronal modelling: quantum harmonic oscillator dynamics in neural structures. Neural Process. Lett. 32(2), 167–199 (2010)
G.G. Rigatos, S.G. Tzafestas, Parallelization of a fuzzy control algorithm using quantum computation. IEEE Trans. Fuzzy Syst. 10, 451–460 (2002)
G.G. Rigatos, S.G. Tzafestas, Quantum learning for neural associative memories. Fuzzy Sets Syst. 157(13), 1797–1813 (2006)
E.T. Rolls, M. Loh, G. Deco, An attractor hypothesis of obsessive compulsive disorder. Eur. J. Neurosci. 28, 782–793 (2008)
R.G. Spencer, Bipolar spectral associative memories. IEEE Trans. Neural Netw. 12, 463–475 (2001)
S.G. Tzafestas, G.G. Rigatos, Stability analysis of an adaptive fuzzy control system using Petri Nets and learning automata. Math. Comput. Simul. 51, 315–339 (2000)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Rigatos, G.G. (2015). Attractors in Associative Memories with Stochastic Weights. In: Advanced Models of Neural Networks. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-43764-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-662-43764-3_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-43763-6
Online ISBN: 978-3-662-43764-3
eBook Packages: EngineeringEngineering (R0)