# Gauge Neural Network with Z(2) Synaptic Variables: Phase Structure and Simulation of Learning and Recalling Patterns

- 40 Downloads

## Abstract

We study the Z(2) gauge-invariant neural network which is defined on a partially connected random network and involves Z(2) neuron variables \(S_i\) (\(=\pm \)1) and Z(2) synaptic connection (gauge) variables \(J_{ij}\) (\(=\pm \)1). Its energy consists of the Hopfield term \(-c_1S_iJ_{ij}S_j\), double Hopfield term \(-c_2 S_iJ_{ij}J_{jk} S_k\), and the reverberation (triple Hopfield) term \(-c_3 J_{ij}J_{jk}J_{ki}\) of synaptic self interactions. For the case \(c_2=0\), its phase diagram in the \(c_3-c_1\) plane has been studied both for the symmetric couplings \(J_{ij}=J_{ji}\) and asymmetric couplings (\(J_{ij}\) and \(J_{ji}\) are independent); it consists of the Higgs, Coulomb and confinement phases, each of which is characterized by the ability of learning and/or recalling patterns. In this paper, we consider the phase diagram for the case of nonvanishing \(c_2\), and examine its effect. We find that the \(c_2\) term enlarges the region of Higgs phase and generates a new second-order transition. We also simulate the dynamical process of learning patterns of \(S_i\) and recalling them and measure the performance directly by overlaps of \(S_i\). We discuss the difference in performance for the cases of Z(2) variables and real variables for synaptic connections.

## Keywords

Hopfield model Gauge neural network Phase diagram Higgs phase Confinement phase Simulation of learning and recalling process## Notes

### Acknowledgements

The authors would like to thank Dr. Yuki Nakano and Mr. Munetada Juta for discussion.

## References

- 1.Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 79:2554–2558MathSciNetCrossRefzbMATHGoogle Scholar
- 2.Haykin S (1994) Neural networks; a comprehensive foundation. Prentice Hall, New JerseyzbMATHGoogle Scholar
- 3.Matsui T (2001) Gauge symmetry and neural networks. In: Janke W et al (eds) Fluctuating paths and fields. World Scientific, Singapore, pp 271–280 (cond-mat/0112463)CrossRefGoogle Scholar
- 4.Kemuriyama M, Matsui T, Sakakibara K (2005) Gauged neural network: phase structure, learning, and associative memory. Physica A 356:525–553 (cond-mat/0203136)CrossRefGoogle Scholar
- 5.Yang C-N, Mills RL (1954) Conservation of isotopic spin and isotopic gauge invariance. Phys. Rev. 96:191–195MathSciNetCrossRefzbMATHGoogle Scholar
- 6.Wegner FJ (1971) Duality in generalized ising models and phase transitions without local order parameters. J. Math. Phys. 12:2259MathSciNetCrossRefGoogle Scholar
- 7.Wilson KG (1974) Confinement of quarks. Phys. Rev. D 10:2445–2458CrossRefGoogle Scholar
- 8.Takafuji Y, Nakano Y, Matsui T (2012) Z(2) gauge neural network and its phase structure. Physica A 391:5258–5304 (arXiv:1206.1110)CrossRefGoogle Scholar
- 9.Fujita Y, Matsui T (2002) Quantum gauged neural network: U(1) gauge theory. In: Wang L et al (ed) Proceedings of 9th international conference on neural information processing, pp 1360–1367 (arXiv:cond-mat/0207023)
- 10.Fujita Y, Hiramatsu T, Matsui T (2005) Quantum gauged neural networks: learning and recalling. In: Proceedings of international joint conference on neural networks. Montreal, Canada, pp 1108–1113Google Scholar
- 11.Sakane S, Hiramatsu T and Matsui T (2016) Neural network for quantum brain dynamics: 4D CP1+U(1) gauge theory on lattice and its phase structure. In: Proceedings pati IV of neural information processing 23rd international conference, ICONIP 2016, Kyoto, Japan, October 16–21, pp 522–530. (arXiv:1610.05433)
- 12.Ichinose I, Matsui T (2014) Lattice gauge theory for condensed matter physics: ferromagnetic superconductivity as its example. Mod. Phys. Lett. B28(1-33):1430012. (arXiv:1408.0089)
- 13.Drouffe JM (1980) Large dimensional lattice gauge theories: (I). Z2 pure gauge system. Nucl. Phys. B 170:211–227MathSciNetCrossRefGoogle Scholar
- 14.Elitzur S (1975) Impossibility of spontaneously breaking local symmetries. Phys. Rev. D 12:3978–3982CrossRefGoogle Scholar
- 15.Hebb DO (1949) The organization of behavior: a neuropsychological theory. Wiley, New YorkGoogle Scholar
- 16.Murai A, Matsui T (2016) Asymmetric synaptic connections in Z(2) gauge neural network. In: Proceedings pati IV of neural information processing 23rd international conference, ICONIP 2016, Kyoto, Japan, October 16–21, 522–530Google Scholar
- 17.Metropolis N, Rosenbluth AW, Rosenbluth MN, Teller AM, Teller E (1953) Equation of state calculations by fast computing machines. J. Chem. Phys. 21:1087–1092CrossRefGoogle Scholar
- 18.Gell-Mann M, Hartle JB (1993) Classical equations for quantum systems. Phys. Rev. D 47:3345–3382MathSciNetCrossRefGoogle Scholar
- 19.van Kampen NG (1981) Stochastic processes in physics and chemistry. Elsevier, AmsterdamzbMATHGoogle Scholar