Hide menu

732A96 Advanced Machine Learning

Course information

Course description

The course covers some advanced models in machine learning. The models are analyzed mainly from a Bayesian perspective.

The course is organized into four topics:
- Graphical Models
- Hidden Markov Models
- State-space models
- Gaussian Process Regression and Classification

Each topic includes lectures, a computer lab and a follow-up seminar.


Course literature

- The book Pattern recognition and machine learning (PRML) by Bishop.
- The article A Review of Bayesian Networks and Structure Learning by Koski and Noble.
- The article Local Computations with Probabilities on Graphical Structures and Their Applications to Expert Systems by Lauritzen and Spiegelhalter.
- The article An Introduction to Hidden Markov Models and Bayesian Networks by Ghahramani.
- The article Explicit-Duration Markov Switching Models by Chiappa.
- The book Gaussian Processes for Machine Learning by Rasmussen and Williams.
- The book Probabilistic Robotics by Thrun et al.
- The article Gaussian Process Networks by Friedman and Nachman.
- The article A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning by Brochu et al.
- Slides.


Topic 1: Graphical Models

Teacher: Jose M. Peña
Read: PRML Chapter 8, Koski and Noble, and Lauritzen and Spiegelhalter.

Lecture 1: Bayesian and Markov Networks Slides
Lecture 2: Probabilistic Reasoning Slides
Lecture 3: Parameter Learning Slides
Lecture 4: Structure Learning Slides

Lab 1: Lab. Submit your report via LISAM. Note that you have to submit an individual and a group report. A group consists of four people. Let the examiner know the composition of your group asap
Seminar 1


Topic 2: Hidden Markov Models

Teacher: Jose M. Peña
Read: PRML Chapter 13.1-13.2, Ghahramani, and Chiappa Sections 3.1-3.3.

Lecture 5: Dynamic Bayesian Networks and Hidden Markov Models Slides
Lecture 6: Autoregressive and Explicit-Duration Hidden Markov Models Slides

Lab 2: Lab. Submit your report via LISAM
Seminar 2


Topic 3: State-Space Models

Teacher: Jose M. Peña
Read: PRML Chapter 13.3 and pages from Probabilistic Robotics

Lecture 7: Linear Gaussian State Space Models and the Kalman Filter Slides
Lecture 8: Extended, Unscented, and Particle Kalmar Filters Slides
Lecture 9: Learning Linear Gaussian State Space Models Slides

Lab 3: Lab. Submit your report via LISAM
Seminar 3


Topic 4: Gaussian Process Regression and Classification

Teacher: Jose M. Peña
Read: PRML Chapters 6.4.1-6.4.6, Friedman and Nachman, Brochu et al., and Gaussian Processes for Machine Learning Chapters 2.1-2.5, 3.1-3.4.1, 3.7, 5.1-5.4.1.

Lecture 10: Gaussian Process Regression Slides
Lecture 11: Kernels, Hyperparameter Learning and More Slides
Lecture 12: Gaussian Process Classification Slides

Lab 4: Lab. Submit your report via LISAM
Seminar 4

Extras: Web applet for playing around with a simple GP | Chapter on kernels from David Duvenaud's PhD thesis.
Packages: kernlab with Vignette
Code: R code for simulating from a GP | Quick demo of the R package kernlab | An even quicker demo of GPs in Matlab.
Data: Lidar | JapanTemp | CanadianWages


Other Material:

- The course has an open GitHub repository where much of the course material can be downloaded.
- The course also has LISAM page.


Page responsible: Jose M. Pe˝a
Last updated: 2018-10-08