Evolving, training and designing neural network ensembles

Previous work on evolving neural networks has focused on single neural networks. However, monolithic neural networks are too complex to train and evolve for large and complex problems. It is often better to design a collection of simpler neural networks that work cooperatively to solve a large and complex problem. The key issue here is how to design such a collection automatically so that it has the best generalisation. This talk introduces work on evolving neural network ensembles, negative correlation learning, and multi-objective approaches to ensemble learning. The links among different learning algorithms are discussed. Online/incremental learning using ensembles will also be presented briefly.