DOI: 10.14704/nq.2017.15.1.1008

Quantum Neural Machine Learning: Backpropagation and Dynamics

Carlos Pedro Gonçalves

Abstract


The current work addresses quantum machine learning in the context of Quantum Artificial Neural Networks such that the networks’ processing is divided in two stages: the learning stage, where the network converges to a specific quantum circuit, and the backpropagation stage where the network effectively works as a self-programing quantum computing system that selects the quantum circuits to solve computing problems. The results are extended to general architectures including recurrent networks that interact with an environment, coupling with it in the neural links’ activation order, and self-organizing in a dynamical regime that intermixes patterns of dynamical stochasticity and persistent quasiperiodic dynamics, making emerge a form of noise resilient dynamical record.

Keywords


Quantum Artificial Neural Networks; Machine Learning; Open Quantum Systems; Complex Quantum Systems

Full Text:

Full Text PDF

References


Aharonov Y, Anandan J, Popescu S and Vaidman L. Superpositions of time evolutions of a quantum system and a quantum time-translation machine. Phys. Rev. Lett. 1990; 64(25):2965-2968.

Akhmet M and Fen MO. Generation of cyclic/toroidal chaos by Hopfield neural networks. Neurocomputing, 2014; 145:230-239.

Behrman EC, Niemel J, Steck JE, Skinner SR. A Quantum Dot Neural Network, In: T. Toffoli T and M. Biafore, Proceedings of the 4th Workshop on Physics of Computation, Elsevier Science Publishers, Amsterdam, 1996; 22-24.

Bertschinger N and Natschläger T. Real-time computation at the edge of chaos in recurrent neural networks. Neural Comput., 2004; 16(7):1413-36.

Brukner . Quantum causality. Nature Physics, 2014; 10:259-263.

Chiribella G, D’ Ariano GM, Perinotti P and Valiron B. Quantum computations without definite causal structure. Phys. Rev. A, 2013; 88(2):022318.

Chrisley R. Quantum learning, In: Pylkkänen P and Pylkkö P (eds.), New directions in cognitive science: Proceedings of the international symposium, Saariselka, 4-9 August, Lapland, Finland, Finnish Artificial Intelligence Society, Helsinki, 1995; 77-89.

Crutchfield JP and Young K. Computation at the Onset of Chaos, In: Zurek W. Entropy, Complexity, and the Physics of Information. SFI Studies in the Sciences of Complexity. Proceedings Volume VIII in the Sante Fe Institute Studies in the Sciences of Complexity, Addison-Wesley, Reading, Massachusetts, 1990; 223-269.

Gonçalves CP. Quantum Cybernetics and Complex Quantum Systems Science - A Quantum Connectionist Exploration. NeuroQuantology, 2015a; 13(1): 35-48.

Gonçalves CP. Financial Market Modeling with Quantum Neural Networks. Review of Business and Economics Studies, 2015b; 3(4):44-63.

Gorodkin J, Sørensen A and Winther O. Neural Networks and Cellular Automata Complexity. Complex Systems, 1993, 7:1-23.

Grassberger P and Proccacia I. Characterization of strange attractors. Phys. Rev. Lett, 1983a; 50:346-349.

Grassberger P and Proccacia I. Measuring the Strangeness of Strange Attractors. Physica D, 1983b; 9:189-208.

Haake F, Ku M and Scharf R. Classical and Quantum Chaos for a Kicked Top. Z. Phys. B. - Condensed Matter, 1987; 65:381-395.

Ivancevic VG and Ivancevic TT. Quantum Neural Computation, Springer, Dordrecht, 2010.

Kak S. Quantum Neural Computing. Advances in Imaging and Electron Physics, 1995; 94:259-313.

Kaplan D and Glass L. Understanding Nonlinear Dynamics. Springer, New York, 1995.

Kauffman SA and Johnsen S. Coevolution to the Edge of Chaos: Coupled Fitness Landscapes, Poised States, and Coevolutionary Avalanches. J. theor. Biol., 1991; 149:467-505.

Kauffman SA. The Origins of Order: Self-Organization and Selection in Evolution. Oxford University Press, New York, 1993.

Langton C. Computation at the Edge of Chaos: Phase Transitions and Emergent Computation. Physica D, 1990; 42:12-37.

Menneer T and Narayanan A. Quantum-inspired Neural Networks, technical report R329, Department of Computer Science, University of Exeter, Exeter, United Kingdom, 1995.

Menneer T Quantum Artificial Neural Networks, Ph. D. thesis, The University of Exeter, UK, 1998.

Nayfeh, AH and Balachandran, B. Applied Nonlinear Dynamics - Analytical, Computational and Experimental Methods, Wiley-VCH, Germany, 2004.

Packard, NH. Adaptation toward the edge of chaos. University of Illinois at Urbana-Champaign, Center for Complex Systems Research, 1988.

Procopio LM, Moqanaki A, Araújo M, Costa F, Calafell IA, Dowd EG, Hamel DR, Rozema LA, Brukner and Walther P. Experimental superposition of orders of quantum gates. Nature Communications, 2015; 6:7913.

Schuld M, Sinayskiy I and Petruccione F. The quest for a Quantum Neural Network. Quantum Information Processing, 2014a; 13(11): 2567-2586.

Schuld M, Sinayskiy I and Petruccione F. Quantum walks on graphs representing the firing patterns of a quantum neural network. Phys. Rev. A, 2014b; 89: 032333.

Watanabe M, Aihara K and Kondo S. Self-organization dynamics in chaotic neural networks. Control Chaos Math. Model., 1997; 8:320-333

Wolfram S. A New Kind of Science. Wolfram Research, Canada, 2002.

Zou Y. Exploring Recurrences in Quasiperiodic Dynamical Systems. Ph. D. Thesis, University of Potsdam, 2007.


Supporting Agencies

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.



| NeuroScience + QuantumPhysics> NeuroQuantology :: Copyright 2001-2017