This research is supported by the long-term strategic development financing of the Institute of Computer Science (RVO:67985807).

Ing. Dušan Húsek, CSc.

(Dusan Husek)

proposed a neural network paradigm capable of solving Boolean factor analysis problems. We are convinced that the potentiall of these NNs is not exhausted yet. So we see it as promising to try, in near future to develop an effective  clustering method o this type of NNs.

Brain Computer interface

Bio inspired computational methods for data analysis.

 

Research:

We study mathematical foundations of brain computer interface (BCI). Mainly computational methods of signal analysis, classification, localization and interpretation. Our main challenge is to use BCI for  post stroke rehabilitation.

Methods for discovering hidden structures of high dimensional binary data are one of the most important challenges facing the machine learning research community. There are many approaches in the literature that try to solve this this hard task.

Based on our knowledge gained by analyzing autoassociative neural networks, we have