This talk is on the identification of complex dynamical systems with recurrent neural networks. The learning of the network parameters is only a subsection of such an effort - even more important is the understanding of the underlying process and its translation into an appropriate network architecture. Thus, not data alone but the interchange with the conceptual thinking is the basis of a successful application. We will see this style of thinking in combination with several real world applications in the talk.
Please note the unusual day and hour
ATS Seminars Organisers: H. Burkhardt (BE), M. Modena (TE), T. Stora (EN)
If you are using Internet Explorer, please use Firefox, Chrome or Edge instead.
Otherwise, please update your browser to the latest version to use Indico without problems.