Czech
English
Institute of Information Theory and Automation
You are here
Projects
Dept.: AS
Duration: 2020
- 2022
Blind inverse problems (i.e. inverse problems with unknown parameters of the forward model)
are well studied for models with uniform grids, such as blind image deconvolution or blind signal
separation. Recently, new methods of learning of non-linear problems with differentiable
nonlinearities (i.e. neural networks) have been proposed, however they rely on supervised
learning on a training set...
Dept.: AS
Duration: 2018
- 2020
Anomaly detection, which aims to identity samples very different from majority, is an important tool of unsupervised data analysis. Currently, most methods for anomaly detection use relatively simple shallow models without any complex layers and hierarchies. This in sharp contrast to the area of supervised classification, where hierarchical models with large number of layers stacked on top of...
Dept.: AS
Duration: 2014
- 2017
This proposal brings together experts in information theory with experts in atmospheric dispersion modelling, to tackle a particularly difficult and highly relevant scientific problem. The overall goal of this project is to develop methods for determining the source term of an accidental release of radionuclides or other hazardous substances into the atmosphere which is suitable for both real-...
Dept.: AS
Duration: 2011
- 2014
The aim of this project is to explore new directions in diagnostics, control and parameter identification strategies of ac electric drives under critical operating conditions. Main attention will be paid to sensorless drive control and estimation in standstill and low speeds. We propose to explore suitability of methods from Bayesian identification and stochastic control in this area. High...
Dept.: AS
Duration: 2008
- 2010
Stochastic decentralized control of distributed systems is studied from theoretical and algorithmic point of view. Decentralization is formalized by imposing conditional independence assumptions in the centralized control problem. However, local models and aims are in general incompatible with this structure and a suitable projections must be found. A range of probabilistic approaches has been...