Learning of Classifier Agents based on Incremental Genetic Algorithms

摘要

Incremental learning has been widely addressed in the machine learning literature to cope with learning tasks where the learning environment is ever changing or training samples become available over time. This paper employs genetic algorithm (GA) as a basic learning algorithm and proposes incremental genetic algorithms (IGA) for incremental learning within one or more classifier agents in a multi-agent environment. We evaluate IGA with two benchmark classification databases. The simulation results show that IGA can be successfully used for incremental learning and speeds up the learning process as compared to the traditional GA.