## Venue

Mondays 14:15 to 16:00, Philweg 12 / SR## First meeting / Assignments

The first meeting will be Monday, October 14th, 2019## Seminar topics:

**INTRODUCTION**- Basic ideas of machine learning
- Training a network (backpropagation)

**THEORY**- A high-bias, low-variance introduction to Machine Learning for physicists

(https://arxiv.org/pdf/1803.08823.pdf) - Hopfield Neural Networks

(J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities", Proceedings of the National Academy of Sciences of the USA, vol. 79 no. 8 pp. 2554–2558, April 1982.) - On the equivalence of Hopfield Networks and Boltzmann Machines

(https://arxiv.org/pdf/1105.2790v3.pdf) - Unsupervised Learning and Generative Models

(Ackley, David H., Geoffrey E. Hinton, and Terrence J. Sejnowski. “A learning algorithm for Boltzmann machines.” Cognitive science 9.1 (1985): 147–169.) - Deep Boltzmann Machines

(Salakhutdinov, Ruslan, and Hinton, Geoffrey E. “Deep Boltzmann Machines.” Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics. 2009.) - Statistical Mechanics of Learning : Generalization

(http://www.ki.tu-berlin.de/fileadmin/fg135/publikationen/opper/Opar95.pdf) - Variational inference in machine learning (Ising model and machine learning)

(https://jaan.io/how-does-physics-connect-machine-learning/) - Spin Glasses, Proteins and Neural Networks

(Bryngelson, Joseph D., and Peter G. Wolynes. “Spin glasses and the statistical mechanics of protein folding.” Proceedings of the National Academy of Sciences 84.21 (1987): 7524–7528.) - Solving the Schrödinger equation with deep learning

(https://becominghuman.ai/solving-schrödingers-equation-with-deep-learning-f9f6950a7c0e) - Quantum machine learning

(https://en.wikipedia.org/wiki/Quantum_machine_learning) - Neural Quantum States

(https://towardsdatascience.com/neural-quantum-states-4793fdf67b13)

- A high-bias, low-variance introduction to Machine Learning for physicists
**NEW IDEAS**- Physics-guided Neural Network (PGNN)

(https://arxiv.org/pdf/1710.11431.pdf) - Hamiltonian Neural Networks

(https://arxiv.org/pdf/1906.01563.pdf) - Learning Hyperparameters for Neural Network Models using Hamiltonian Dynamics

(http://www.cs.toronto.edu/dcs/theses/MSc/2000-01/Choo.msc.pdf) - Synergy of physics-based reasoning and machine learning in biomedical applications: towards unlimited deep learning with limited data

(https://www.tandfonline.com/doi/full/10.1080/23746149.2019.1582361) - Identifying topological order through unsupervised machine learning

(https://www.nature.com/articles/s41567-019-0512-x) - Deep Fluids: A Generative Network for Parameterized Fluid Simulations

(https://arxiv.org/pdf/1806.02071.pdf

- Physics-guided Neural Network (PGNN)