next up previous contents index
Next: 9.9.7 Summary Up: Optimization Methods for Previous: 9.9.5 Experiment: the Dichotomy

9.9.6 Experiment: Time Series Prediction


In this case, the task is to predict the next value in the sequence (ergodic and chaotic) generated by the logistic map [Lapedes:87a], according to the recurrence relation:

We tried different architecture and obtained a speedup of 400-500, and slightly better generalization properties for the BFGS optimization method presented.

In general, we obtained a larger speedup for problems with high-precision requirements (using real values for inputs or outputs). See also [Battiti:89a].

Guy Robinson
Wed Mar 1 10:19:35 EST 1995