Combining Artificial Neural Nets

The chapters in this volume consist of articles written by leading researchers in the field of Combining Artificial Neural Nets, and as such provide a unique coverage of the area. The techniques that are presented include ensemble-based, and modular approaches. The presentation of techniques is accompanied by analysis and evaluation of their relative effectiveness, and by reports of ther application to a variety of problems. The chapters make clear the effectiveness of combining in increasing performance, and the limitations of using a simple unitary net. For this reason this volume should be required reading for all those concerned with any applications of artificial neural nets where good generalisation performance is important.