Machine Learning 2017

Welcome to WASP Summer School on Machine Learning 2017.

The WASP GSM recommends that every PhD student who have received a certification of completion for the summer school gets 1.5hp.

KTH 7-11 of August

All lectures will be in room Q31 on Osquldas väg 6B.

Monday, 7 th of August
13.00-18  Bayesian networks, dynamic Bayesian networks and hidden Markov models, José Peña, LiU [PDF]
18-19 Dinner
19-21 Lab on graphical models [PDF, solution]

Tuesday, 8th of August
09.00-12 Statistical relational learning and probabilistic programming part I, Luc De Raedt and Anton Dries, KU Leuven, Belgium [PDF, practical session 1]
12-13 Lunch
13.00-18 Statistical relational learning and probabilistic programming part II, Luc De Raedt and Anton Dries, KU Leuven, Belgium [PDF, practical session 2, practical session 3, practical session 4, practical session 5 , solutions]

The tutorial will provide a motivation for, an overview of and an introduction to the fields of statistical relational learning and probabilistic programming. These combine rich expressive relational representations with the ability to learn, represent and reason about uncertainty. The tutorial will introduce a number of core concepts concerning representation and inference.  It shall focus on probabilistic extensions of logic programming languages, such as CLP(BN), BLPs, ICL, PRISM, ProbLog, LPADs, CP-logic, SLPs and DYNA, but also discusses relations to alternative probabilistic programming languages such as Church, IBAL and BLOG and to some extent to statistical relational learning models such as RBNs, MLNs, and PRMs.

The concepts will be illustrated on a wide variety of tasks, including models representing Bayesian networks, probabilistic graphs, stochastic grammars, etc. This should allow participants to start writing their own probabilistic programs. We further provide an overview of the different inference mechanisms developed in the field, and discuss their suitability for the different concepts. We also touch upon approaches to learn the parameters of probabilistic programs, and mention a number of applications in areas such as robotics, vision, natural language processing, web mining, and bioinformatics.

The tutorial will consist of a theoretical part and will also provide hands-on exercises with the probabilistic programming language ProbLog.
The tutorial is to a very large extent based on earlier tutorials in collaboration with Angelika Kimmig.

Wednesday, 9th of August
09.00-12 Gaussian Processes part I, Marc Deisenroth, Imperial College London, UK [GP slides]
12-13 Lunch
13.00-18 Gaussian Processes part II, Marc Deisenroth, Imperial College London, UK [BO slides, tutorial, research slides]

Thursday, 10th of August
09.00-12 Deep Learning part I, Josephine Sullivan, KTH [intro, classification, gradient, layered, CNN, tutorial (Python-files are in our Box)]
12-13 Lunch
13.00-18 Deep Learning part II, Josephine Sullivan, KTH

More information can be found on the KTH Deep Learning Course web page.

Friday, 11th of August
09.00-12 Student research presentations

  • Bayesian Frequency Tracking – How To Approximate, and How Not To, Martin Lindfors, LiU
  • Combining Machine Learning with Invariants Assurance Techniques for Autonomous Systems, Piergiuseppe Mallozzi, Chalmers
  • Denoising Autoencoders, Vidit Saxena, Ericsson/KTH
  • Olov Andersson, LiU

12-13 Lunch