|
Machine Learning for Physicists (PW)5 ECTS (englische Bezeichnung: Machine Learning for Physicists)
Modulverantwortliche/r: Florian Marquardt Lehrende:
Florian Marquardt
Startsemester: |
SS 2017 | Dauer: |
1 Semester | Turnus: |
unregelmäßig |
Präsenzzeit: |
28 Std. | Eigenstudium: |
122 Std. | Sprache: |
Englisch |
Lehrveranstaltungen:
Inhalt:
This is a course introducing modern techniques of machine learning, especially deep neural networks, to an audience of physicists. Neural networks can be trained to perform many challenging tasks, including image recognition and natural language processing, just by showing them many examples. While neural networks have been introduced already in the 70s, they really have taken off in the past decade, with spectacular successes in many areas. Often, their performance now surpasses humans, as proven by the recent achievements in handwriting recognition and in winning the game of 'Go' against expert human players. They are now also being considered more and more for applications in physics, ranging from predictions of material properties to analyzing phase transitions. We will cover the basics of neural networks (backpropagation), convolutional networks, autoencoders, restricted Boltzmann machines, and recurrent neural networks, as well as the recently emerging applications in physics. Time permitting, we will address other topics, like the relation to spin glass models, curriculum learning, reinforcement learning, adversarial learning, active learning, "robot scientists", deducing nonlinear dynamics, and dynamical neural computers.
Lernziele und Kompetenzen:
Learning goals and competences:
Students
Weitere Informationen:
www: http://www.thp2.nat.uni-erlangen.de/index.php/2017_Machine_Learning_for_Physicists,_by_Florian_Marquardt
Verwendbarkeit des Moduls / Einpassung in den Musterstudienplan: Das Modul ist im Kontext der folgenden Studienfächer/Vertiefungsrichtungen verwendbar:
- Materials Physics (Master of Science)
(Po-Vers. 2015s | NatFak | Materials Physics (Master of Science) | Master's examination | Materials physics elective course)
Studien-/Prüfungsleistungen:
Machine Learning for Physicists (Prüfungsnummer: 557267)
(englischer Titel: Machine Learning for Physicists)
- Prüfungsleistung, mündliche Prüfung, Dauer (in Minuten): 30, benotet, 5 ECTS
- Anteil an der Berechnung der Modulnote: 100.0 %
- weitere Erläuterungen:
Masterstudierende mit Studienbeginn ab Sommersemester 2015 können Prüfungen in deutscher Sprache nur mit Genehmigung des Prüfungsausschussvorsitzenden ablegen.
- Erstablegung: SS 2017, 1. Wdh.: SS 2017 (nur für Wiederholer)
1. Prüfer: | Florian Marquardt |
|
|
|
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|