David Barbour <[email protected]> writes:

> There are actually several ways to compose predictive/learning systems. The
> simple compositions: they can be chained, hierarchical, or run in parallel
> (combining independent estimates). More complicated composition: use
> speculative evaluation to feed predicted behaviors and sensory inputs back
> into the model. (Speculation is also useful in on-the-fly planning loops
> and constraint models.)

One important way to compose learning systems is co-evolution. This
couples the learning processes, rather than the predictions, and can
result composite systems which are more powerful/accurate than the sum
of their parts.

Cheers,
Chris
_______________________________________________
fonc mailing list
[email protected]
http://vpri.org/mailman/listinfo/fonc

Reply via email to