We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...
We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An eectiveperformance measure is the minimax re...
This paper addresses how to quickly recognize a character pattern using a lot of case examples without learning. Here without learning means just finding the most similar example...
This paper introduces XCSF extended with tile coding prediction: each classifier implements a tile coding approximator; the genetic algorithm is used to adapt both classifier cond...
Pier Luca Lanzi, Daniele Loiacono, Stewart W. Wils...
The impact of learning on evolution in dynamic environments undergoes recognized stages of the Baldwin Effect although its cause is not clear. To identify it experimentally, we de...