Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems
Amanda J.C. Sharkey
Springer London, Jan 22, 1999 - Computers - 298 pages
The past decade could be seen as the heyday of neurocomputing: in which the capabilities of monolithic nets have been well explored and exploited. The question then is where do we go from here? A logical next step is to examine the potential offered by combinations of artificial neural nets, and it is that step that the chapters in this volume represent. Intuitively, it makes sense to look at combining ANNs. Clearly complex biological systems and brains rely on modularity. Similarly the principles of modularity, and of reliability through redundancy, can be found in many disparate areas, from the idea of decision by jury, through to hardware re dundancy in aeroplanes, and the advantages of modular design and reuse advocated by object-oriented programmers. And it is not surprising to find that the same principles can be usefully applied in the field of neurocomput ing as well, although finding the best way of adapting them is a subject of on-going research.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Other editions - View all
2-torus accuracy Adaboost Addemup Advances in Neural algorithm approximation architecture Artificial Neural Networks backpropagation bagging best NN bias boosting bootstrap boundary Breiman chapter classifiers collinearity combination-weights component networks correlation covariate cues data sets distribution domain theory effective Equation Error a Error error rate estimate examples factor factorial encoding function Gaussian IEEE improve input manifold joint encoding linear combinations Machine Learning matrix mean squared error methods mixture models Mixtures of Experts modified weak model modular modules MSE-OLC Neural Computation Neural Information Processing neural nets neurons node normalisation object depth obtained optimal order statistics output overfitting parameters performance posterior probabilities prediction predictor problem reduced regression sample Schapire Section selection selection algorithms simple average speech recognition stereo term test set tion Touretzky training data training set trees true MSE validation set values variables variance vector vergence vergence angle viewing distance weak learners weight decay