Hauptseminar: Deep Learning for Physics

Written Assignments

Daniil Kudrin Installation and Introduction to Python and Tensorflow
Krish Ramesh Gradient Decent	PDF
Javier Pasarin Lopez Logistic Regression and Ising Hamiltonian (without Susy)
Felix Puster Feed Forward Deep Neural Networks (Ising Hamiltonian)
Max Staats Convolutional Networks, High-Level Concepts	PDF
Sebastian Bürger Energy Based Models, Boltzmann Learning
Camila Bräutigam Restricted Boltzmann Machines
Stefan Tsankov STM Machine Learning	PDF
Caspar Pirker Variational Autoencoders and Generative Adversarial Networks

Talks

Talks take place Wednesdays 15:15-16:00 via Zoom.

Wednesday 13.05.2020, 15:15	Daniil Kudrin Installation and Introduction to Python and Tensorflow	PDF 1	PDF 2
Wednesday 20.05.2020, 15:15	Krish Ramesh Gradient Decent	Slides	Code	Video
Wednesday 27.05.2020, 15:15	Javier Pasarin Lopez Logistic Regression and Ising Hamiltonian (without Susy)	Slides	Code	Video
Wednesday 03.06.2020, 15:15	Felix Puster Feed Forward Deep Neural Networks (Ising Hamiltonian)	Slides	Code	Video
Wednesday 10.06.2020, 15:15	Max Staats Convolutional Networks, High-Level Concepts	Slides	Code	Video
Wednesday 17.06.2020, 15:15	Sebastian Bürger Energy Based Models, Boltzmann Learning	Slides		Video
Wednesday 24.06.2020, 15:15	Camila Bräutigam Restricted Boltzmann Machines	Slides	Code	Video
Wednesday 08.07.2020, 15:15	Stefan Tsankov STM Machine Learning	Slides		Video
Wednesday 15.07.2020, 15:15	Caspar Pirker Variational Autoencoders and Generative Adversarial Networks	Slides		Video

Course Information

Recommended Reading:	Rev. Mod. Phys. 91, 045002 (2019), Machine learning and the physical sciences, PDF
	Physics Reports 810 1–124 (2019), A high-bias, low-variance introduction to Machine Learning for physicists, PDF
	Nature volume 570 484–490 (2019), Machine learning in electronic-quantum-matter imaging experiments, PDF