Next: ACKNOWLEDGEMENTS
Up: DISCUSSION / OUTLOOK
Previous: LIMITATIONS
There are a few obvious directions for
ongoing experimental research:
(1) Use larger time windows - they seem to be
promising even for off-line methods (see the last
paragraph of section 4).
(2) Thoroughly test the potential of on-line methods.
Both (1) and (2) should greatly benefit from fast hardware.
(3) Compare performance
of predictive coding based on neural predictors
to the performance of predictive coding
based on different kinds of predictors.
Juergen Schmidhuber
2003-02-25