Verwandte Artikel zu Deep Learning in Physics: An Introduction
Inhaltsangabe
The book introduces the reader to Deep Learning, an advanced machine learning method to analyze data and find patterns by means of self-adapting, self-improving neural networks. After an overview of the fundamentals, the book explains the different network architectures used in Deep Learning and the different learning methods such as energy-driven, reductionist and success target learning. The last part deals with the advanced concepts of Deep Learning such as weak and unsupervised training and hybrid network architectures.
Die Inhaltsangabe kann sich auf eine andere Ausgabe dieses Titels beziehen.
Über die Autorin bzw. den Autor
Martin Erdmann is Professor of Experimental Physics at RWTH Aachen University, Germany, since 2004. He studied physics at the Universities of Cologne and Freiburg, worked as a researcher at the Fermi lab in Chicago, and obtained his PhD from the University of Freiburg in 1990. He finished his habilitation at the University of Heidelberg in 1996 and subsequently worked as a Heisenberg Fellow at the German Electron Synchrotron (DESY) in Hamburg and as a lecturer at the University of Karlsruhe. He is an experienced lecturer and author of undergraduate textbooks on physics. Jonas Glombitza is PhD student at RWTH Aachen University, Germany, in the area of high energy physics. For the analysis of his research experiments he develops and extensively uses Deep Learning methods. Gregor Kasieczka is Associate Professor at the University of Hamburg, Germany, in the area of particle physics. He obtained his PhD from the University of Heidelberg in 2013 and subsequently was post-doctoral researcher at the ETH Zurich, Switzerland, before taking up his current position. Uwe Klemradt is Professor of Condensed Matter Physics at RWTH Aachen University, Germany.
„Über diesen Titel“ kann sich auf eine andere Ausgabe dieses Titels beziehen.
