Ústav teorie informace a automatizace

Jste zde


Středa, 24 Srpen, 2022

The seminar is postponed.

The speaker will be Soňa Molnárová, the seminar will be held xxx in the AS-meeting room 474.

Čtvrtek, 28 Červenec, 2022

The speaker will be Rudolf Kulhavý, seminar will be held on Thursday 28. 7. 2022 at 13:00 in the AS-meeting room 474.

The world of practical applications of modeling and optimization is rich, colorful, and hard to overlook. The seminar will attempt to yield more insight by structuring the space of opportunities around three dimensions of every economic activity, namely Product (design) Process (improvement) Customer (management) A range of real-life applications in multiple industries will be used to illustrate the classification.

Úterý, 26 Červenec, 2022

20.7.2022 po těžké nemoci odešel pan Petr Nedoma.

Byl to velice přátelský a dobrý člověk, spolehlivý kolega a věrný kamarád.

Vzpomínáme na něj..

Středa, 25 Květen, 2022

The speaker will be Miroslav Kárný, the seminar will be held on Wednesday 25.5.2022 at 11:00 in the AS-meeting room 474. 

Pondělí, 16 Květen, 2022

The speaker will be Tereza Siváková, the seminar will be held on Monday 16. 5. 2022 at 11 am in the AS-meeting room 474

Pondělí, 9 Květen, 2022

Speaker will be Tereza Siváková.

The research studies optimal decision-making with the focus on preferences quantified for fully probabilistic design (FPD). FPD models the closed DM loop and the agent’s preferences by joint probability densities (pds). There is a preference-elicitation (PE) principle, which maps the agent’s model of the state transitions and its incompletely expressed wishes on an ideal pd quantifying them. This research also studies preferences targeting actions and contradicting preferences.

Pátek, 8 Duben, 2022

Naše oddělení podalo 4 grantové návrhy do GAČR (3 standardní a jeden je spolupráce s Koreí): 

  • M.Kárný - Probabilistic description of beliefs and wishes for prescriptive dynamic decision making 
  • O.Tichý - Bayesian non-linear source quantification of spatio-temporal atmospheric emissions
  • K.Belda - Predictive control design under bounded uncertainties and disturbances in estimated states and parameters of robotic systems
  • K.Belda (spolunavrhovatel) - Controllable gripping mechanics: Modelling, control and experiments

Držíme palce!

Pondělí, 4 Duben, 2022


Speaker will be Marko Ruman.

Deep reinforcement learning has shown an ability to achieve super-human performance in solving complex reinforcement learning tasks only from raw-pixels. However, it fails to reuse knowledge from previously learnt tasks to solve new, unseen ones. To generalize and reuse knowledge is one of the fundamental requirements for creating a truly intelligent agent. The work summarizes the problem of transfer learning in reinforcement learning tasks and offers a method for one-to-one task transfer learning.

Čtvrtek, 31 Březen, 2022

Department of Adaptive Systems, Institute of Information Theory and Automation, Czech Academy of Sciences is looking for researchers/postdocs/PhD students in one of the areas:
• - Cybernetics
• - Artificial intelligence
• - Informatics
• - Applied mathematics
• - Control theory
• - other related fields

Good professional knowledge of English is essential, no knowledge of Czech is needed.

If you are interested please contact Mrs Neuner neuner@utia.cas.cz for further details. Those who have started PhD in Ukraine are also welcome.

Čtvrtek, 24 Březen, 2022

Marko Ruman složil státní doktorskou zkoušku s vyznamenáním (obor: Matematické inženýrství, FJFI ČVUT) a úspešně představil teze své práce na téma "Transfer Learning in Reinforcement Learning".