Summary
International Symposium on Nonlinear Theory and its Applications
2005
Session Number:2-1-3
Session:
Number:2-1-3-2
Learning wave phenomena on the CNN universal machine
Samuel Xavier-de-Souza, Johan A.K. Suykens, Joos Vandewalle,
pp.590-593
Publication Date:2005/10/18
Online ISSN:2188-5079
Summary:
In recent years it was discovered that cellular neural networks with local and space-invariant connections are able to generate a wide range of two-dimensional spatiotemporal behavior. Many of these dynamics can be directly mapped into natural phenomena occurring in physics, chemistry, and biology. These mappings make cellular neural network a suitable tool for modeling and simulation of such phenomena. With the advent of advanced VLSI implementations of this network and its inherent parallelism, simulations can be executed on-chip in a fraction of the time that would be necessary with actual digital computer implementations. In this work we introduce a methodology for the learning of this kind of dynamics. The problem is treated as an optimization problem and is based on trajectory learning for recurrent neural networks. In order to adapt this to the learning of two-dimensional dynamics, we proposed a cost function which can incorporate time instants into the set of variables to be optimized. As a result it can be observed that the network can also learn any frequency modulation of the original dynamics. Besides simulation, the proposed methodology can also be applied directly to a VLSI implementation of the network. Experiments were performed for the spiral autowave.