New Challenges in Neural Computation (NC²)

Workshop of the GI-Fachgruppe Neuronale Netze and the German Neural Networks Society in connection to DAGM 2012, Graz

[Home][Call for Papers][Program]

Topic

Neural computation and biologically inspired data processing systems constitute essential topics in artificial intelligence accompanied by a well established theoretical foundation and numerous successful applications in science and industry. Although some of the most popular methods such as support vector machines or self-organizing maps are well established and readily available in commercial tools, modern information processing continues to pose challenging tasks to the field. Not only the amount of data explodes in virtually all application areas but also their complexity with regard to dimensionality, structural variety, and multimodality. At the same time, the tasks become more and more complex, moving from simple classification or prediction in pattern recognition to involved learning scenarios in dynamic environments with no explicit single objective. Humans are capable of handling complex situations and tasks by means of a combination of different paradigms, whereas existing neural systems mostly mirror only one or a few facets of the whole game.

A non-exhaustive list of topics tackled in the workshop is given by the following keywords:

nonlinear dimensionality reduction, blind source separation, and visualization
neural models for very large or streaming data sets
parallelization and neural hardware
neural models for non-euclidean data
interpretable models
recursive models and dynamic systems
applications

Submission

We welcome submissions in one of the three following tracks:

ongoing research, long paper (up to 8 pages in LNCS style)
ongoing research, short paper (up to 2 pages in LNCS style)
open problems and challenges (up to 2 pages in LNCS style)

All papers should be prepared using the Springer LNCS style and sent as pdf to Barbara Hammer by e-mail (bhammer@techfak.uni-bielefeld.de) until 22.7.2012.

Publication

All contributions will be published online in the TR series Machine Learning Report (with ISBN). There will be the possibility to submit extended versions of the contributions to a special issue of the journal Neurocomputing.

Contact

For further questions, please contact the workshop organizers

Barbara Hammer, CITEC, Faculty of Technology, Bielefeld University, D-33594 Bielefeld, bhammer@techfak.uni-bielefeld.de
Thomas Villmann, Mathematics, University of Applied Sciences Mittweida, Technikumplatz 17, D-09648 Mittweida, villmann@hsmw.de