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
