DeepAI AI Chat
Log In Sign Up

Learning the Ising Model with Generative Neural Networks

by   Francesco D'Angelo, et al.
ETH Zurich

Recent advances in deep learning and neural networks have led to an increased interest in the application of generative models in statistical and condensed matter physics. In particular, restricted Boltzmann machines (RBMs) and variational autoencoders (VAEs) as specific classes of neural networks have been successfully applied in the context of physical feature extraction and representation learning. Despite these successes, however, there is only limited understanding of their representational properties and limitations. To better understand the representational characteristics of both generative neural networks, we study the ability of single RBMs and VAEs to capture physical features of the Ising model at different temperatures. This approach allows us to quantitatively assess learned representations by comparing sample features with corresponding theoretical predictions. Our results suggest that the considered RBMs and convolutional VAEs are able to capture the temperature dependence of magnetization, energy, and spin-spin correlations. The samples generated by RBMs are more evenly distributed across temperature than those of VAEs. We also find that convolutional layers in VAEs are important to model spin correlations.


page 1

page 2

page 3

page 4

page 6

page 7

page 8

page 12


DCTRGAN: Improving the Precision of Generative Models with Reweighting

Significant advances in deep learning have led to more widely used and p...

Deep Learning the Ising Model Near Criticality

It is well established that neural networks with deep architectures perf...

Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow

Theoretical understanding of how deep neural network (DNN) extracts feat...

Restricted Boltzmann Machine Flows and The Critical Temperature of Ising models

We explore alternative experimental setups for the iterative sampling (f...

Deep representation learning for human motion prediction and classification

Generative models of 3D human motion are often restricted to a small num...

A survey on Variational Autoencoders from a GreenAI perspective

Variational AutoEncoders (VAEs) are powerful generative models that merg...

The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems

Generative Autoregressive Neural Networks (ARNN) have recently demonstra...