All ML algorithms depend on data representation – efficient and appropriate data representation can enable better understanding of parameters that affect the variations in the data. Representations can be tailored or learned and are dependent on the domain in which classification or prediction algorithms are deployed in.

Recent techniques on representation learning consider unsupervised learning, deep learning, including advances in probabilistic models, auto-encoders, manifold learning and deep networks. One important research question is the ability of the model to achieve abstraction and invariance. In terms of abstraction, we mean the ability of the model to generate abstract concepts from more simple ones. This is then closely related to the amount of data one needs to learn the model or the representation. One of the focus areas will be development of models that encode various levels of abstraction and that are also based on multimodal input data. We will also strive to test this through invariance ability given that models encoding various abstraction levels are invariant to variations in input data. This is closely related to the symbol grounding problem, still largely unsolved in AI, robotics and NLP areas. We will also work on combining representation learning with reasoning techniques and common sense logic. For this reason, statistical-relation learning will also be a methodology to investigate.

Doctoral students

Student Supervisor
Svante Linusson
Henrik Hult
Wojciech Chachólski

Wojciech Chachólski

Benoit Baudry
Sonja Buchegger
Benoit Baudry
Daniel Ahlsen Valentin Goranko
Martin Monperrus
Wojciech Chachólski
Martin Monperrus

Industrial doctoral students

Student Organisation Supervisor
Tobii Alexandre Proutiere
Shuangshuang Chen Volvo Mårten Björkman
Jonathan Styrud ABB Christian Smith
David Molin Tobii Josephine Sullivan
Alexandra Karlsson SAAB Magnus Jansson
SEB Henrik Hult
AstraZenica Kevin Smith
Johan Haslum AstraZenica Kevin Smith
Univrses Atsoto Maki
Belongs to: Wallenberg AI, Autonomous Systems and Software Program
Last changed: Jan 09, 2019