Logical Reasoning for Revealing the Critical Temperature through Deep Learning of Configuration Ensemble of Statistical Systems
arXiv:1901.03817 · doi:10.7566/JPSJ.88.054002
Abstract
Recently, there have been many works on the deep learning of statistical ensembles to determine the critical temperature of a possible phase transition. We analyze the detailed structure of an optimized deep learning machine and prove the basic equalities among the optimized machine parameters and the physical quantities of the statistical system. According to these equalities, we conclude that the bias parameters of the final full connection layer record the free energy of the statistical system as a function of temperature. We confirm these equalities in one- and two-dimensional Ising spin models and actually demonstrate that the deep learning machine reveals the critical temperature of the phase transition through the second difference of bias parameters, which is equivalent to the specific heat. Our results disprove the previous works claiming that the weight parameters of the full connection might play a role of the order parameter such as the spin expectation.
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Mutual Information, Neural Networks and the Renormalization Group
- Detection of phase transition via convolutional neural network
- An exact mapping between the Variational Renormalization Group and Deep Learning
- Neural Network Renormalization Group
- Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
- Deep Neural Network Detects Quantum Phase Transition
- Restricted Boltzmann Machines for the Long Range Ising Models
- RG inspired Machine Learning for lattice field theory
- Examples of renormalization group transformations for image sets
- Finite-Range Scaling Method to Analyze Systems with Infinite-Range Interactions