The Theory of Deep Learning - Part I

Why do modern deep neural networks (DNNs) perform so well on previously unseen test data, even when their number of weights is much larger than the number of data points in the training set? This question keeps puzzling many theorists and practicioners doing Deep Learning (DL), in particular those who …

Machine Learning Topological Defects in the XY Model

Machine learning can detect classical topological defects in materials

Tensor Networks: Putting Quantum Wavefunctions into Machine Learning

Tensor networks are a powerful tool for compressing quantum wavefunctions developed in the physics community. Parameterizing a special class of models with tensor networks brings the full power of tensor networks to machine learning tasks.

Machine Learning and Quantum Mechanics

How do quantum mechanics and machine learning fit together?