Skip to main content
top

Pro všechny

Stránka je přístupná i mimo doménu utia.

Seminar User‘s feedback in Preference elicitation

Zařazeni
Type of Event
Importance
Content Access

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.

Submitted by neuner on

Seminar Transfer learning in Reinforcement learning tasks

Zařazeni
Type of Event
Importance
Content Access

 

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.

Submitted by neuner on

Job offer - Help Ukraine

Zařazeni
Type of Event
Importance
Content Access

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.

Submitted by neuner on

Announcement of an open competition for the position of the Director of the Institute of Information Theory and Automation of the Czech Academy of Sciences

Zařazeni
Type of Event
Importance
Content Access
Visible Thereafter
Ne

The Board of the Institute of Information Theory and Automation of the Czech Academy of Sciences (Ústav teorie informace a automatizace AV ČR, v. v. i.) announces an open competition for the position of the Director of the Institute.

Submitted by zajicek on

Vladimír Kučera is the laureate of the National Government Prize Czech Mind

Zařazeni
Type of Event
Importance
Content Access
Visible Thereafter
Ano

Prof. Ing. Vladimir Kucera, DrSc., dr. h. c. is an Emeritus Scientist of the Czech Academy of Sciences and served as the Director of the UTIA from 1990-1998. He has been a longtime excelent researcher at the Department of Control Theory, his scientific activities in UTIA range over 50 years. More about the prize on https://www.ciirc.cvut.cz/en/profesor-vladimir-kucera-ziskal-nejvyssi-vedecke-vyznamenani-ceskou-hlavu/

Photo: BcA. ONDŘEJ KALMÁN

Submitted by souckova on

Velké říjnové soft-computingové rokování 2021

Zařazeni
Type of Event
Importance
Content Access

VŘSR is a traditional workshop sequentially organized by colleagues from UTIA, IRAFM Ostrava University, and UI. The meeting is focused mainly on the presentation of fresh (inter) results of participating doctoral students and their subsequent discussion in a wider plenary of experienced science matadors. Contributions traditionally come from different areas of uncertainty processing.

Submitted by kratochvil on

Statistics of Machine Learning

Zařazeni
Type of Event
Importance
Content Access

Institutes of Information Theory and Automation in cooperation with Humboldt-Universität zu Berlin and Faculty of Mathematics and Physics, Charles University in Prague organizes STAT of ML (Statistics of Machine Learning) conference to be held from  October 6 to October 7, 2021  in Prague, Czech Republic. The main theme of the conference is rigorous statical treatment of machine learning applied in the field of digital finance.

 More information can be found at the webpage 

Submitted by dostalova on
Subscribe to Pro všechny