Backpropagation training in adaptive quantum networks

DOI10.1007/S10773-009-0103-1zbMATH Open1204.81042arXiv0903.4416OpenAlexW2114257374MaRDI QIDQ616804FDOQ616804

C. Altman, Roman R. Zapatrin

Publication date: 12 January 2011

Published in: International Journal of Theoretical Physics (Search for Journal in Brave)

Abstract: We introduce a robust, error-tolerant adaptive training algorithm for generalized learning paradigms in high-dimensional superposed quantum networks, or emph{adaptive quantum networks}. The formalized procedure applies standard backpropagation training across a coherent ensemble of discrete topological configurations of individual neural networks, each of which is formally merged into appropriate linear superposition within a predefined, decoherence-free subspace. Quantum parallelism facilitates simultaneous training and revision of the system within this coherent state space, resulting in accelerated convergence to a stable network attractor under consequent iteration of the implemented backpropagation algorithm. Parallel evolution of linear superposed networks incorporating backpropagation training provides quantitative, numerical indications for optimization of both single-neuron activation functions and optimal reconfiguration of whole-network quantum structure.

Full work available at URL: https://arxiv.org/abs/0903.4416

Recommendations

• scientific article; zbMATH DE number 2033237
• Quantum neural networks
• Quantum neural nets
• Some quantum neural networks
• Quantum neural network
• Neural networks with quantum architecture and quantum learning
• Quantum gate Elman neural network and its quantized extended gradient back-propagation training algorithm
• Learning algorithm and application of quantum BP neural networks based on universal quantum gates
• A quantum model of feed-forward neural networks with unitary learning algorithms
• Application of fractional theory in quantum back propagation neural network

zbMATH Keywords

neural networksadaptive learningquantum topology

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Quantum algorithms and complexity in the theory of computing (68Q12) Quantum computation (81P68) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• On the foundations of combinatorial theory I. Theory of M�bius Functions
• Experimental Realization of Deutsch’s Algorithm in a One-Way Quantum Computer
• Finitary algebraic superspace
• Connectionism, cognitive maps and the development of objectivity
• Algebraic description of spacetime foam
• Superpositional quantum network topologies

Cited In (3)

• Superpositional quantum network topologies
• Quantum continual learning of quantum data realizing knowledge backward transfer
• Adjoint-operators and non-adiabatic learning algorithms in neural networks

This page was built for publication: Backpropagation training in adaptive quantum networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q616804)