Hochschule Darmstadt - Fb Informatik

Drucken| Layout| Design| Schriftgröße English|
Modulbeschreibung
Module:Introduction to Machine Learning
Module numbers:30.2588 [PVL 30.2589]
Language:english
Study programme:Bachelor 2014 - Katalog I: Anwendungs- und systemorientierte Module
Bachelor dual KoSI 2014 - Katalog I: Anwendungs- und systemorientierte Module
Bachelor KMI 2014 - Katalog I: Anwendungs- und systemorientierte Module
Bachelor 2007 - Vertiefung AE: Application Engineering
KoSI 2007 - Vertiefung AE: Application Engineering
KoSI 2007/2004/2003/2002/99 - Wahlpflichtfächer aus dem Informatikbereich
Type of course:V+P = Lecture+Practical
Weekly hours:3+1
Credit Points:5
Exam:Accompanying tests and evaluation of the solution of the problem sets
Registering for examimplicitly by booking
PVL (e.g. Practical):not graded
Frequency of offering:guest lecture (lastly in WS 2019/2020)
Required knowledge:linear algebra, statistics, basics of programming
Learning objectives:The students will be able to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.
Content:1. Linear Regression with One Variable
2. Linear Algebra Review
3. Linear Regression with Multiple Variables
4. Logistic Regression
5. Regularization
6. Neural Networks: Representation
7. Neural Networks: Learning
8. Deep Learning
9. Decision trees
10. Machine Learning System Design
11. Unsupervised Learning (clustering)
12. Dimensionality Reduction
13. Anomaly Detection
14. Recommender Systems
15. Large Scale Machine Learning
Literature:1. Mitchell, Tom. Machine Learning. New York, NY: McGraw-Hill, 1997. ISBN: 9780070428072.
2. https://ww​w.coursera​.org/learn​/machine-l​earning​
3. MacKay, David. Information Theory, Inference, and Learning Algorithms. Cambridge, UK: Cambridge University Press, 2003. ISBN: 9780521642989. Available on-line http://www​.inference​.phy.cam.a​c.uk/macka​y/itila/bo​ok.html​
Lecture style / Teaching aids:15 Lessons with 4 problemsets
Responsibility:Arnim Malcherek
Released:SS 2017
Offered in WS 19/20:Rapp / Svyatov
Professional competencies:
  • formal, algorithmic, mathematical competencies: high
  • analytical, design and implementation competencies: high
  • technological competencies: high
  • capability for scientific work: low
Interdisciplinary competencies:
  • project related competencies: medium
  • interdisciplinary expertise: basic technical and natural scientific competence
  • social and self-competencies: analytical competence, competence of knowledge acquisition, fluency

[Fachbereich Informatik] [Hochschule Darmstadt]
© 2008 - 2019 FBI OBS Team. Alle Rechte vorbehalten.