Fundamental problems in statistical physics XIV: Lecture on Machine Learning
arXiv:2202.05670 · doi:10.1016/j.physa.2022.128154
Abstract
The recent progresses in Machine Learning opened the door to actual applications of learning algorithms but also to new research directions both in the field of Machine Learning directly and, at the edges with other disciplines. The case that interests us is the interface with physics, and more specifically Statistical Physics. In this short lecture, I will try to present first a brief introduction to Machine Learning from the angle of neural networks. After explaining quickly some fundamental models and global aspects of the training procedure, I will discuss into more detail two examples illustrate what can be done from the Statistical Physics perspective.
References in corpus (22)
- Auto-Encoding Variational Bayes
- An Introduction to Variational Autoencoders
- Message Passing Algorithms for Compressed Sensing
- Machine learning phases of matter
- Tutorial on Variational Autoencoders
- Statistical physics of inference: Thresholds and algorithms
- Phase transition in the detection of modules in sparse networks
- Phase Transitions in the Coloring of Random Graphs
- Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models
- Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes
- Emergence of Compositional Representations in Restricted Boltzmann Machines
- The Nishimori line and Bayesian Statistics
- Mean-field message-passing equations in the Hopfield model and its generalizations
- Beyond neural scaling laws: beating power law scaling via data pruning
- Phase Diagram of Restricted Boltzmann Machines and Generalised Hopfield Networks with Arbitrary Priors
- Restricted Boltzmann Machine, recent advances and mean-field theory
- Phase transitions in Restricted Boltzmann Machines with generic priors
- Thermodynamics of Restricted Boltzmann Machines and related learning dynamics
- Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval
- Learning a Restricted Boltzmann Machine using biased Monte Carlo sampling
- 'Place-cell' emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space
- From complex to simple : hierarchical free-energy landscape renormalized in deep neural networks