Lecture: Machine Learning

Announcements

You have an opportunity to review your exams on the following dates:

• Friday 02.03.2018 13:00 - 14:00
• Friday 02.03.2018 14:00 - 15:00
• Friday 02.03.2018 15:00 - 16:00

and

• Friday 09.03.2018 13:00 - 14:00
• Friday 09.03.2018 14:00 - 15:00
• Friday 09.03.2018 15:00 - 16:00

These are the only dates that we will be offering. If you cannot make it you can optionally ask one of your fellow colleagues to attend the review for you. For this you'll need to sign an authorization form. Here is a simple template that you can use.

To be able to efficiently process all the requests and avoid long queues, in order to review your exam you must sign up using this Moodle form.

The grades (including the homework bonus) will be published in a few days.

Tentative list of topics

• Introduction
  • What is machine learning?
  • Typical tasks in ML
• k-Nearest neighbors
  • kNN for classification and regression
  • Distance functions
  • Curse of dimensionality
• Decision trees
  • Constructing & pruning decision trees
  • Basics of information theory
• Probabilistic inference
  • Parameter estimation
  • Maximum likelihood principle
  • Maximum a posteriori
  • Full Bayesian approach
• Linear regression
  • Linear basis function models
  • Overfitting
  • Bias-variance tradeoff
  • Model selection
  • Regularization
• Linear classification
  • Perceptron algorithm
  • Generative / discriminative models for classification
  • Linear discriminant analysis
  • Logistic regression
• Optimization
  • Gradient-based methods
  • Convex optimization
  • Stochastic gradient descent
• Support vector machines
  • Maximum margin classification
  • Soft-margin SVM
  • Constrained optimization
• Kernel methods
  • Kernel trick
  • Kernelized linear regression
• Deep learning
  • Feedforward neural networks
  • Backpropagation
  • Advanced architectures
  • Adaptive step-size selection
• Dimensionality reduction
  • Principal component analysis
  • Singular value decomposition
  • Probabilistic PCA
• Mixture models
  • Gaussian mixture models
  • K-means
  • Topic models
  • EM algorithm
• Variational inference
  • Posterior inference in latent variable models
  • Mean-field approximation
  • Evidence lower bound

Literature

• Pattern Recognition and Machine Learning. Christopher Bishop. Springer-Verlag New York. 2006.
• Machine Learning: A Probabilistic Perspective. Kevin Murphy. MIT Press. 2012

Schedule

• Lecture:
  • Monday 10:00 - 12:00, room MW 0001
• Practical session:
  • Tuesday 12:00 - 14:00, room MW 0001
    (occasionally used as a lecture slot)
  • Wednesday 16:00 - 18:00, room MI HS1
• Homework discussion: Thursday 8:00 - 10:00, room 00.08.059

Organizational details

• Language: English
• Intended audience:
  • Master students of the Informatics department (Including Data Engineering & Analytics program)
  • Not available for Information Systems (Wirtschaftsinformatik) students
• New regulation: Please note that you can only include one of IN2064 / IN2332 in your curriculum
• 8 ECTS
• Grade bonus of 0.3 will be awarded to students who show sufficient work for at least 75% of the homework sheets. Note, that the grades 1.0, 4.3, 4.7 and 5.0 can't be improved.
• All course material will be made available via Piazza