Construction of a Neural Network with Temperature-Dependent Recall Patterns

TL;DR

This paper introduces a neural network model that switches recall patterns based on temperature, using different graph structures to encode patterns and demonstrating phase transition behavior through simulations.

Contribution

The paper presents a novel neural network model that exhibits temperature-dependent recall switching by embedding patterns into different graph structures, supported by simulation evidence.

Findings

Recall pattern changes with temperature due to graph structure differences

System undergoes a first-order phase transition during recall switching

High free-energy barriers can prevent pattern recall at low temperatures

Abstract

We present a simple model that recalls two different patterns depending on the temperature. To realize a change in recall pattern due to temperature change, we embed two patterns to different graphs: the first pattern into a fully connected graph and the second pattern into a sparse graph. Because a fully connected graph is more resistant to thermal fluctuations than a sparse graph, we can realize a change in recall pattern by tuning relative weights of the two patterns properly. We demonstrate by equilibrium Monte-Carlo simulations that such a temperature-dependent change in recall patterns does occur in our model. Simulation results strongly indicate that the system undergoes a first-order phase transition when the change in recall patterns occurs. It is also demonstrated by annealing simulations that the system fails to recall the pattern embedded in the sparse graph at low temperatures if the free-energy barrier is too high to overcome within the given simulation timescale.