Quantum gauged neural network: U(1) gauge theory

  title={Quantum gauged neural network: U(1) gauge theory},
  author={Yukari Fujita and Tetsuo Matsui},
  journal={Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02.},
  pages={1360-1367 vol.3}
  • Y. Fujita, T. Matsui
  • Published 30 June 2002
  • Physics
  • Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02.
A quantum model of neural network is introduced and its phase structure is examined. The model is an extension of the classical Z(2) gauged neural network of learning and recalling to a quantum model by replacing the Z(2) variables, S/sub i/ = /spl plusmn/1 of neurons and J/sub ij/ = /spl plusmn/1 of synaptic connections, to the U(1) phase variables, S/sub i/ = exp(i/spl phi//sub i/) and J/sub ij/ = exp(i/spl theta//sub ij/). These U(1) variables describe the phase parts of the wave functions… 

Figures from this paper

Quantum gauged neural networks: learning and recalling
The quantum effects are found to reduce the performance of quantum neural networks on a 3D lattice, where J/sub x/spl mu// are regarded as gauge variables connecting nearest-neighbor sites.
Neural Network for Quantum Brain Dynamics: 4D CP ^1 1 +U(1) Gauge Theory on Lattice and Its Phase Structure
A system of two-level quantum quasi-spins and gauge bosons put on a 3+1D lattice is considered, which becomes a model of quantum brain dynamics proposed by Umezawa et al., where spins and gauge field describe water molecules and photons, respectively.
Modeling Quantum Mechanical Observers via Neural-Glial Networks
It is shown that, when the number of neurons and astrocytes is exponentially large, the degrees of freedom of the dynamics of the neural and glial networks can be completely removed and, consequently, that the retention time of the superposition of the wave functions in the brain is as long as that of the microscopic quantum system of pre-synaptics sites.
Quantum fluctuations in a scale-free network-connected Ising system
Abstract.We study the effect of quantum fluctuations in an Ising spin system on a scale-free network of degree exponent γ>5 using a quantum Monte Carlo simulation technique. In our model, one can
Gauge Neural Network with Z(2) Synaptic Variables: Phase Structure and Simulation of Learning and Recalling Patterns
The phase diagram for the case of nonvanishing Z(2) gauge-invariant neural network is considered, and it is found that the c2 term enlarges the region of Higgs phase and generates a new second-order transition.
Quantum-Inspired Complex-Valued Multidirectional Associative Memory
  • Naoki Masuyama, C. Loo
  • Computer Science
    2015 International Joint Conference on Neural Networks (IJCNN)
  • 2015
This paper introduces Quantum-Inspired Complex-Valued Multidirectional Associative Memory (QCMAM) to handle multi-valued information and presents mathematical proofs of parallelism and unitarity for a complex-valued model.
Training a Quantum Neural Network
Results on several real-world data sets show that this algorithm can train the proposed quantum neural networks, and that it has some advantages over classical learning algorithms.
Forecasting Financial Risk using Quantum Neural Networks
There has been enormous attention in quantum algorithms for reinforcing machine learning (ML) algorithms. In the current paper, we present quantum neural networks (QNNs) and a method of training
O ct 2 00 2 LU-ITP 2002 / 013 KANAZAWA-0216 ITEP-LAT-2002-07 RCNP-Th 02014 String Breaking and Monopoles : a Case Study in the 3 D Abelian Higgs Model
We study the breaking of the string spanned between test charges in the three dimensional Abelian Higgs model with compact gauge field and fundamentally charged Higgs field at zero temperature. In


Gauge Symmetry and Neural Networks
A new model of neural network is proposed that possesses local gauge symmetry and resembles lattice gauge theory of high-energy physics, and predicts a new phase corresponding to confinement phase, in which brain loses ablility of learning and memory.
The importance of quantum decoherence in brain processes
  • Max Tegmark
  • Physics
    Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics
  • 2000
It is argued that the degrees of freedom of the human brain that relate to cognitive processes should be thought of as a classical rather than quantum system, i.e., that there is nothing fundamentally wrong with the current classical approach to neural network simulations.
Confinement of Quarks
A mechanism for total confinement of quarks, similar to that of Schwinger, is defined which requires the existence of Abelian or non-Abelian gauge fields. It is shown how to quantize a gauge field
The background, basic sources of data, concepts, and methodology to be employed in the study of perceptrons are reviewed, and some of the notation to be used in later sections are presented.
Neural networks and physical systems with emergent collective computational abilities.
  • J. Hopfield
  • Computer Science
    Proceedings of the National Academy of Sciences of the United States of America
  • 1982
A model of a system having a large number of simple equivalent components, based on aspects of neurobiology but readily adapted to integrated circuits, produces a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.
Physics, Mathematics, and Minds. (Book Reviews: The Emperor's New Mind. Concerning Computers, Minds, and the Laws of Physics.)
From the Publisher: In The Emporer's New Mind, eminent physicist Roger Penrose argues that there are facets of human thinking, of human imagination, that can never be emulated by a machine.
“Neural” computation of decisions in optimization problems
Results of computer simulations of a network designed to solve a difficult but well-defined optimization problem-the Traveling-Salesman Problem-are presented and used to illustrate the computational power of the networks.
Stochastic processes in physics and chemistry
Preface to the first edition. Preface to the second edition. Abbreviated references. I. Stochastic variables. II. Random events. III. Stochastic processes. IV. Markov processes. V. The master