Account
Edit tools
Intern
SucheSearch
English

Foundations for Maschine Learning (SS2018): Unterschied zwischen den Versionen

Aus International Center for Computational Logic
Wechseln zu:Navigation, Suche
Romy Thieme (Diskussion | Beiträge)
Keine Bearbeitungszusammenfassung
Romy Thieme (Diskussion | Beiträge)
Keine Bearbeitungszusammenfassung
Zeile 1: Zeile 1:
{{Vorlesung
{{Vorlesung
|Title=Academic Skills in Computer Science
|Title=Foundations for Machine Learning
|Research group=Wissensverarbeitung
|Research group=Wissensverarbeitung
|Lecturers=Steffen Hölldobler;
|Lecturers=Yohanes Stefanus
|Tutors=Johannes Fichte (starting from 01.05.)
|Term=SS
|Term=SS
|Year=2018
|Year=2018
|Module=INF-04-FG-SWT, INF-AQUA, MCL-CS
|Module=MCL-AI, MCL-PI, INF-BAS2, INF-VERT2
|SWSLecture=2
|SWSLecture=4
|SWSExercise=2
|SWSExercise=2
|SWSPractical=0
|SWSPractical=0
|Exam type=mündliche Prüfung
|Exam type=mündliche Prüfung
|Description====Description===
|Description=Content
The topic of this course is mathematical foundations for Machine Learning. We define the term "machine learning" to mean the automated detection of meaningful patterns in data.
Nowadays machine learning based technologies are ubiquitous: digital economic systems, web search engines, anti-spam software, credit/insurance fraud detection software, accident prevention systems, bioinformatics, etc.
This course provides a theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations that transform these principles into practical algorithms, such as algorithms appropriate for big data learning. We will start with Valiant's PAC (Probably Approximately Correct) learning model, the ERM (Empirical Risk Minimization) learning rule, the No-Free-Lunch Theorem, and the VC (Vapnik-Chervonenkis) dimension. The course will end with deep learning.


This lecture is aiming at providing basic skills in reading, understanding, and evaluating scientific articles, and in presenting scientific results in presentations and publications. It includes topics like citations and bibliographic data in scientific publications,  selection of topics, examples, and results for an oral presentation, preparation of slides and other materials for oral presentations as well as selecting, structuring, and writing scientific articles. The lecture will include practical training in reading and reviewing scientific articles, in preparing and giving presentations, and in setting up and writing short scientific articles. The topics will be selected from Computational Logic. Hence, some familiarity with propositional and first-order logic is assumed.  
Schedule
The lecture will take place from 11th June till 20th July 2018 in room APB2026 on the following days:
Mondays 4. DS (1pm - 2:30pm); starting on 11th June 2018
Tuesdays 2. DS (9:20am - 10:50am)
Thursdays 2. DS (9:20am - 10:50am)


Prerequisites
Probability Theory
Linear Algebra
Algorithm Design & Analysis


===Schedule===


The lecture will take place on Mondays 4.DS (1pm - 2:30pm) and on Thursdays 6. DS (4:40pm - 6:10pm) in room '''APB E005'''.
The lecture will start on Monday, 9th April, 2018.
}}
}}

Version vom 9. April 2018, 14:13 Uhr

Foundations for Machine Learning

Lehrveranstaltung mit SWS 4/2/0 (Vorlesung/Übung/Praktikum) in SS 2018

Dozent

  • Yohanes Stefanus

Umfang (SWS)

  • 4/2/0

Module

Leistungskontrolle

  • Mündliche Prüfung


Content The topic of this course is mathematical foundations for Machine Learning. We define the term "machine learning" to mean the automated detection of meaningful patterns in data. Nowadays machine learning based technologies are ubiquitous: digital economic systems, web search engines, anti-spam software, credit/insurance fraud detection software, accident prevention systems, bioinformatics, etc. This course provides a theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations that transform these principles into practical algorithms, such as algorithms appropriate for big data learning. We will start with Valiant's PAC (Probably Approximately Correct) learning model, the ERM (Empirical Risk Minimization) learning rule, the No-Free-Lunch Theorem, and the VC (Vapnik-Chervonenkis) dimension. The course will end with deep learning.

Schedule The lecture will take place from 11th June till 20th July 2018 in room APB2026 on the following days: Mondays 4. DS (1pm - 2:30pm); starting on 11th June 2018 Tuesdays 2. DS (9:20am - 10:50am) Thursdays 2. DS (9:20am - 10:50am)

Prerequisites Probability Theory Linear Algebra

Algorithm Design & Analysis




Abgerufen von „https://iccl.inf.tu-dresden.de/w/index.php?title=Foundations_for_Maschine_Learning_(SS2018)&oldid=25534“