252-0220-00L  Introduction to Machine Learning

SemesterFrühjahrssemester 2018
DozierendeA. Krause
Periodizitätjährlich wiederkehrende Veranstaltung
KommentarPreviously called Learning and Intelligent Systems

Prof. Krause approves that students take distance exams, also if the exam will take place at a later time due to a different time zone of the alternative exam place.
To get Prof. Krause's signature on the distance exam form please send it to Rita Klute, Link.


252-0220-00 VIntroduction to Machine Learning
Die Vorlesung findet jeweils (Di 13-15 und Mi 13-15) im ML D 28 mit Videoübertragung im ML E 12 statt.
4 Std.
Di13:15-15:00ML D 28 »
13:15-15:00ML E 12 »
Mi13:15-15:00ML D 28 »
13:15-15:00ML E 12 »
29.05.13:15-15:00HG E 3 »
13:15-15:00HG F 30 »
A. Krause
252-0220-00 UIntroduction to Machine Learning2 Std.
Mo15:15-17:00HG D 1.2 »
Di15:15-17:00HG D 1.2 »
Mi15:15-17:00CAB G 11 »
Fr13:15-15:00ML D 28 »
A. Krause
252-0220-00 AIntroduction to Machine Learning
No presence required.
1 Std.A. Krause


KurzbeschreibungThe course introduces the foundations of learning and making predictions based on data.
LernzielThe course will introduce the foundations of learning and making predictions from data. We will study basic concepts such as trading goodness of fit and model complexitiy. We will discuss important machine learning algorithms used in practice, and provide hands-on experience in a course project.
Inhalt- Linear regression (overfitting, cross-validation/bootstrap, model selection, regularization, [stochastic] gradient descent)
- Linear classification: Logistic regression (feature selection, sparsity, multi-class)
- Kernels and the kernel trick (Properties of kernels; applications to linear and logistic regression; k-NN
- The statistical perspective (regularization as prior; loss as likelihood; learning as MAP inference)
- Statistical decision theory (decision making based on statistical models and utility functions)
- Discriminative vs. generative modeling (benefits and challenges in modeling joint vy. conditional distributions)
- Bayes' classifiers (Naive Bayes, Gaussian Bayes; MLE)
- Bayesian networks and exact inference (conditional independence; variable elimination; TANs)
- Approximate inference (sum/max product; Gibbs sampling)
- Latent variable models (Gaussian Misture Models, EM Algorithm)
- Temporal models (Bayesian filtering, Hidden Markov Models)
- Sequential decision making (MDPs, value and policy iteration)
- Reinforcement learning (model-based RL, Q-learning)
LiteraturTextbook: Kevin Murphy: A Probabilistic Perspective, MIT Press
Voraussetzungen / BesonderesDesigned to provide basis for following courses:
- Advanced Machine Learning
- Data Mining: Learning from Large Data Sets
- Probabilistic Artificial Intelligence
- Probabilistic Graphical Models
- Seminar "Advanced Topics in Machine Learning"


Information zur Leistungskontrolle (gültig bis die Lerneinheit neu gelesen wird)
Leistungskontrolle als Semesterkurs
ECTS Kreditpunkte8 KP
PrüfendeA. Krause
RepetitionDie Leistungskontrolle wird nur in der Session nach der Lerneinheit angeboten. Die Repetition ist nur nach erneuter Belegung möglich.
Prüfungsmodusschriftlich 120 Minuten
Zusatzinformation zum PrüfungsmodusThe final grade will be determined by the written final exam. The project accounts for 30% of the grade, but it will only be counted if it exceeds your exam grade
Hilfsmittel schriftlichTwo A4-pages (i.e. one A4-sheet of paper), either handwritten or 11 point minimum font size.
Diese Angaben können noch zu Semesterbeginn aktualisiert werden; verbindlich sind die Angaben auf dem Prüfungsplan.


Es werden nur die öffentlichen Lernmaterialien aufgeführt.


Keine Informationen zu Gruppen vorhanden.


Keine zusätzlichen Belegungseinschränkungen vorhanden.

Angeboten in

Computational Biology and Bioinformatics MasterTheorieWInformation
Computational Biology and Bioinformatics MasterMethoden der InformatikWInformation
Informatik BachelorVertiefung Computational ScienceOInformation
Informatik BachelorVertiefung Information and Data ProcessingOInformation
Integrated Building Systems MasterVertiefungsfächerWInformation
Mathematik BachelorAuswahl: Weitere GebieteWInformation
Rechnergestützte Wissenschaften BachelorRobotikWInformation
Rechnergestützte Wissenschaften MasterRobotikWInformation
Robotics, Systems and Control MasterKernfächerWInformation