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

Gauge Neural Network with Z(2) Synaptic Variables: Phase Structure and Simulation of Learning and... We study the Z(2) gauge-invariant neural network which is defined on a partially connected random network and involves Z(2) neuron variables $$S_i$$ S i ( $$=\pm $$ = ± 1) and Z(2) synaptic connection (gauge) variables $$J_{ij}$$ J i j ( $$=\pm $$ = ± 1). Its energy consists of the Hopfield term $$-c_1S_iJ_{ij}S_j$$ - c 1 S i J i j S j , double Hopfield term $$-c_2 S_iJ_{ij}J_{jk} S_k$$ - c 2 S i J i j J j k S k , and the reverberation (triple Hopfield) term $$-c_3 J_{ij}J_{jk}J_{ki}$$ - c 3 J i j J j k J k i of synaptic self interactions. For the case $$c_2=0$$ c 2 = 0 , its phase diagram in the $$c_3-c_1$$ c 3 - c 1 plane has been studied both for the symmetric couplings $$J_{ij}=J_{ji}$$ J i j = J j i and asymmetric couplings ( $$J_{ij}$$ J i j and $$J_{ji}$$ J j i 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 $$c_2$$ c 2 , and examine its effect. We find that the $$c_2$$ 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 $$S_i$$ S i and recalling them and measure the performance directly by overlaps of $$S_i$$ S i . We discuss the difference in performance for the cases of Z(2) variables and real variables for synaptic connections. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neural Processing Letters Springer Journals

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

Loading next page...
 
/lp/springer_journal/gauge-neural-network-with-z-2-synaptic-variables-phase-structure-and-rlbnmA5MdD
Publisher
Springer Journals
Copyright
Copyright © 2017 by Springer Science+Business Media, LLC
Subject
Computer Science; Artificial Intelligence (incl. Robotics); Complex Systems; Computational Intelligence
ISSN
1370-4621
eISSN
1573-773X
D.O.I.
10.1007/s11063-017-9678-3
Publisher site
See Article on Publisher Site

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 $$S_i$$ S i ( $$=\pm $$ = ± 1) and Z(2) synaptic connection (gauge) variables $$J_{ij}$$ J i j ( $$=\pm $$ = ± 1). Its energy consists of the Hopfield term $$-c_1S_iJ_{ij}S_j$$ - c 1 S i J i j S j , double Hopfield term $$-c_2 S_iJ_{ij}J_{jk} S_k$$ - c 2 S i J i j J j k S k , and the reverberation (triple Hopfield) term $$-c_3 J_{ij}J_{jk}J_{ki}$$ - c 3 J i j J j k J k i of synaptic self interactions. For the case $$c_2=0$$ c 2 = 0 , its phase diagram in the $$c_3-c_1$$ c 3 - c 1 plane has been studied both for the symmetric couplings $$J_{ij}=J_{ji}$$ J i j = J j i and asymmetric couplings ( $$J_{ij}$$ J i j and $$J_{ji}$$ J j i 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 $$c_2$$ c 2 , and examine its effect. We find that the $$c_2$$ 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 $$S_i$$ S i and recalling them and measure the performance directly by overlaps of $$S_i$$ S i . We discuss the difference in performance for the cases of Z(2) variables and real variables for synaptic connections.

Journal

Neural Processing LettersSpringer Journals

Published: Aug 3, 2017

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off