Abstract

July 3 - 11.40-12.30
N.Ay - On the Geometry of Complexity: an Approach to Neural Information Processing

I am following the general concept that complexity should somehow quantify the deviation of a composed system from being the unrelated collection of its individual constituents. Information geometry provides a powerful framework for a mathematical elaboration of this concept. The aim of my talk is to present analytical results on complex systems and illustrate them by computer simulations. Applying my approach to the field of neural networks, it leads to a generalized version of the infomax principle by Linsker. [an error occurred while processing this directive]