Exploring neural network training strategies to determine phase transitions in frustrated magnetic models

TL;DR

This paper investigates the use of transfer learning and a novel 'confusion' technique with neural networks to identify phase transitions in frustrated magnetic models, demonstrating their effectiveness compared to traditional Monte Carlo methods.

Contribution

It introduces and tests transfer learning and a confusion-based method for phase detection in frustrated spin systems, advancing neural network applications in many-body physics.

Findings

Transfer learning effectively identifies phases in frustrated magnets.

The 'confusion' technique accurately maps phase diagrams.

Neural network results agree with Monte Carlo simulations.

Abstract

The transfer learning of a neural network is one of its most outstanding aspects and has given supervised learning with neural networks a prominent place in data science. Here we explore this feature in the context of strongly interacting many-body systems. Through case studies, we test the potential of this deep learning technique to detect phases and their transitions in frustrated spin systems, using fully-connected and convolutional neural networks. In addition, we explore a recently-introduced technique, which is at the middle point of supervised and unsupervised learning. It consists in evaluating the performance of a neural network that has been deliberately "confused" during its training. To properly demonstrate the capability of the "confusion" and transfer learning techniques, we apply them to a paradigmatic model of frustrated magnetism in two dimensions, to determine its phase diagram and compare it with high-performance Monte Carlo simulations.