Fully probabilistic design of adaptive decision-making strategies suitable under informationally demanding conditions
Leader
Research Context
Identification Code
2C06001
AS
Quantitative lymphoscintigraphy for diagnostics and therapy of upper limbs
Leader
Identification Code
NC7601
Fully probabilistic design of dynamic decision strategies
Leader
Research Context
Identification Code
GA102/08/0567
Model-based control of mechatronic systems for robotics
Leader
Identification Code
GP102/06/P275
Stochastic Modeling of Dynamic Value Networks
Leader
Research Context
Identification Code
IAA700750701
PhD. Topic: Approximation of fully-probabilistic version of dynamic programming as a basis of universal learning, decision-making and control systems (Kárný)
Type of Work
dissertation
Affiliation/Phone
ÚTIA AV ČR, v.v.i., AS department, 266052274
Supervisor
Kárný
Keywords
Adaptive systems, Bayesian learning and decision making, fully probabilistic design of decision strategies, approximation of mulrivariate implicit functions
Fully probabilstic design of dynamic decision startegies is a well-developed theoretical basis of learning decision systems, which are potentially widely applicable in technology, natural and societal systems. The applicability is strongly constrained by complexity of the associated optimisation, a special version of dynamic programming. In the considered case, it is necessary to approximate a scalar function of many variables, which is implictily described as a solution of of non-linear integral-difference equation.
Bibliography
- M. Kárný, T.V.Guy, Fully probabilistic control design, Systems & Control Letters, 55:4, 259-265, 2006
- M. Kárný et al, Optimized Bayesian Dynamic Advising: Theory and Algorithms, Springer, London
- J. Si et al, Handbook of Learning and Approximate Dynamic Programming, Wiley-IEEE Press, Danvers, 2004, ISBN 0-471-66054-X
Note
It can be solved at FJFI or FEL CVUT Prague, ZUC Plzen or elsewhere after agreement.
Adaptive Systems - list of projects
execute_display('page_1',array('AS'));
?>
Content Access
Special Context
Matematická statistika
Nestranné odhady, informační matice, odhady metodou momentů, princip maximální věrohodnosti, eficience, statistická hypotéza, stejnoměrně nejsilnější test, test poměrem věrohodností, neparametrické modely, empirická distribuční funkce, histogram, jádrový odhad hustoty, testy dobré shody, konfidenční množiny, intervaly spolehlivosti.
Analogue Electronics (half-course)
This half-course introduces key modelling classifications for analogue electrical signals and systems, leading notably to small-signal analysis of nonlinear components. There is also a focus on amplifiers, notably on operational amplifier configurations.