Doctoral defence: Anti Ingel “Algorithms using information theory: classification in brain-computer interfaces and characterising reinforcement-learning agents“

On 22. September at 2.15 pm Anti Ingel will defend his thesis "Algorithms using information theory: classification in brain-computer interfaces and characterising reinforcement-learning agents" for obtaining the degree of Doctor of Philosophy (Computer Science).

Prof. Raul Vicente Zafra, University of Tartu;
Assoc. Prof. Dirk Oliver Theis, University of Tartu.

  Prof. Mikhail Prokopenko, University of Sydney (Australia);
  Assoc. Prof. Luigi Bianchi, Tor Vergata University of Rome (Italy).

Information theory is a branch of mathematics that forms a theoretical basis for today's communication technologies. Also, information theory has been used to give definitions of abstract notions like autonomy. This thesis uses just mentioned applications of information theory to tackle problems in different machine-learning frameworks. In the field of communication, brain-computer interfaces (BCIs) were considered. A BCI is a direct communication channel between the user's brain and an external device - thus, it allows controlling devices directly ""by thought"". An external device could be, for example, a computer or an electric wheelchair. A well-working BCI would allow a user to control devices using only brain signals measured with electrodes placed on the head. The second application of information theory, measuring autonomy, was used to characterise the behaviour of reinforcement-learning (RL) agents. RL is a type of machine learning in which an agent learns by getting feedback from an environment.

This thesis introduces algorithms that are based on information theory results. In the case of BCIs, information theory is used to measure the amount of information the BCI can send in a unit of time, acting as an abstract performance measure. The BCI-related contributions tackled the question of whether it is possible to find an optimal classifier for BCIs and under which conditions the rule is optimal. Algorithms that find the optimal classifier are introduced.

In the case of RL agents, information theory is used to quantify the agent's degree of autonomy and other characterising measures. This contribution relies on already existing information-theoretic definitions of autonomy and the agent's internalisation of the environment. Also, an already existing method called partial information decomposition is used. An algorithm is introduced to calculate the information-theoretic measures; this helps to characterise RL agents' behaviour.



21st Estonian Summer School on Computer and Systems Science

Illustration with lines

Opening of the Estonian Centre of Excellence in Artificial Intelligence

Vabariigi Presidendi Kultuurirahastu preemiate laureaadid

Awards of the Cultural Foundation of the President of the Republic given to Hedvig Tamman and Liisa Rätsep