Institute of Information Theory and Automation

Pro všechny

Submission Instructions

Submissions should be at most 6 pages in length in NIPS format (, and should include the title, authors' names, postal and email addresses, and an abstract not to exceed 150 words. Submissions in pdf format only should be sent to: with the subject line "NIPS Workshop" and with the title, authors' names and abstract included in the body of the message.

Important Dates

Call for Contributions


The workshop will include discussed talks and poster sessions. We invite submissions of papers describing the technical content of proposed contribution. The selected submissions may be accepted either as an oral presentation or as a poster presentation. We especially encourage submissions that directly address any of the topics, but related papers are also welcomed.

The workshop’s targeted audience is:


This is a one-day workshop that will follow the 24rd Annual Conference on Neural Information Processing Systems (NIPS 2010), .

The workshop will consist of two 3-hour sessions. There will be 6 invited talks by experts in the area, 4-6 contributed talks and a poster session of contributed papers. There will be time at the end of each talk/session for questions and discussion. A panel discussion moderated by the organisers is scheduled.

Schedule & Presentations





Opening session



"Bounded Rationality in

Multiagent Systems Using


The UTIA's library maintains the collection of books and journals (about 33 500 bound volumes), provides an internet access to electronic publications and databases and offers inter-library loan service. The UTIA's library is a public library.





Jak nastavit proxy server pro přístup do placených databází

Databáze planecené z prostředků ÚTIA vyžadují mít správně nastavený počítač.
Je nutné mít nastavenou tzv. proxy na a port na 8000.

Nastavení ve Firefoxu:

Menu -> Možnosti
Záložka Rozšířené, podzáložka Síť, tlačítko Nastavení připojení ...
Ruční nastavení proxy serverů ...
HTTP proxy:, Port: 8000
+ zaškrtnout "Pro všechny protokoly používat tento proxy server"


Návod na nahlášení publikace

  • Jaké druhy publikací se nahlašují? - seznam zde.
  • Typy publikací - seznam zde.
  • Jméno, heslo pro přihlášení je k dispozici v knihovně.

Bayesian Dynamic Decision Making

Dynamic decision making (DM) maps knowledge into DM strategy, which ensures reaching DM aims under given constraints. Under general conditions, Bayesian DM, minimizing expected loss over admissible strategies, has to be used. Existing limitations of the paradigm impede its applicability to complex DM as:

  1. Complexity of the information processing often crosses resources accessible.
  2. Quantification of domain-specific knowledge, aims and constraints is weakly supported. It concerns mapping of domain-specific elements on probabilistic distributions (pd).
  3. Methodology of the DM with multiple aims is incomplete.

The research aims to overcome these problems. It relies on distributed DM and fully probabilistic design (FPD) of strategies. The goal is to build a firm theoretical background of FPD of distributed DM strategies. Besides, it will enrich available results and unify them into internally consistent theory suitable for a flat cooperation structure.

This aim implies the main tasks:

  1. Inspection of conditions leading to FPD
  2. Extension of FPD to design with sets of ideal pds
  3. Design of computerized conversion of knowledge and aims into environment-describing and ideal pds
  4. Elaboration of theoretical framework for selecting cooperation tools



Active projects

Former projects

Syndicate content
Institute of Information Theory and Automation