View on GitHub

Deep Learning for Physics Research

Information

This page contains additional material for the textbook Deep Learning for Physics Research by Martin Erdmann, Jonas Glombitza, Gregor Kasieczka, and Uwe Klemradt.

The authors can be contacted under authors@deeplearningphysics.org.

For more information on the book, refer to the page by the publisher.

Exercises

Section 1 - Deep Learning Basics

Chapter 3 - Building blocks of neural networks

Chapter 4 - Optimization of network parameters

Chapter 5 - Mastering model building


Section 2 - Standard Architectures of Deep Networks

Chapter 7 - Fully-connected networks: improving the classic all-rounder

Chapter 8 - Convolutional neural networks and analysis of image-like data

Chapter 9 - Recurrent neural networks: time series and variable input

Chapter 10 - Graph networks and convolutions beyond Euclidean domains

Chapter 11 - Multi-task learning, hybrid architectures, and operational reality


Section 3 - Introspection, Uncertainties, Objectives


Section 4 - Deep Learning Advanced Concepts

Chapter 16 - Weakly-supervised classification

Chapter 17 - Autoencoders: finding and compressing structures in data

Chapter 18 - Generative models: data from noise


 

Citation

@book{doi:10.1142/12294,
	  author = {Erdmann, Martin and Glombitza, Jonas and Kasieczka, Gregor and Klemradt, Uwe},
	  title = {Deep Learning for Physics Research},
	  publisher = {WORLD SCIENTIFIC},
	  year = {2021},
	  doi = {10.1142/12294},
	  address = {},
	  edition   = {},
	  URL = {http://deeplearningphysics.org},
	  eprint = {https://worldscientific.com/doi/pdf/10.1142/12294}
}

 

Errata

Please report mistakes to authors@deeplearningphysics.org.

So far, no errors are known.

Usage

Note: To improve the exercise page and potentially improve and extend the scope, we measure the use of the task templates and the interest in the solutions with the tool Google Analytics.