Machine Learning for Quantum Many-body Physics

International Workshop
25 - 29 June 2018

The workshop covers the emerging research area that applies machine learning techniques to analyze, represent, and solve quantum many-body systems in condensed matter physics. This includes problems of phase classification and characterization, state compression, feature extraction, wavefunction representation using neural networks, and connections between tensor networks and  machine learning.

• Supervised phase classification
• Unsupervised learning of quantum phases
• Restricted Boltzmann machines for representing wavefunctions
• Solving quantum many-body problems
• Connections between the renormalization group and deep learning
• Machine learning and density functional theory
• Material discovery using machine learning
• Quantum neural networks
• Quantum error correction and decoding with neural networks
• Quantum state tomography with machine learning