Previous abstract Next abstract

Session 100 - Computational Techniques.
Display session, Thursday, January 18
North Banquet Hall, Convention Center

[100.03] Dynamic Modeling of time series using Artificial Neural Networks

A. D. Nair (Astronomy Dept., Univ. of Florida), J. C. Principe (Computational NeuroEngineering Laboratory, Univ. of Florida)

Artificial Neural Networks (ANN) have the ability to adapt to and learn complex topologies, they represent new technology with which to explore dynamical systems. Multi-step prediction is used to capture the dynamics of the system that produced the time series. Multi-step prediction is implemented by a recurrent ANN trained with trajectory learning. Two separate memories are employed in training the ANN, the common tapped delay-line memory and the new gamma memory. This methodology has been applied to the time series of a white dwarf and to the quasar 3C 345.

Program listing for Thursday