Competition Among Networks Improves Committee Performance

Munro, Paul W., Parmanto, Bambang

Neural Information Processing Systems 

Since a neural network predictor inherently has an excessive number of parameters, reducing the prediction error is usually done by reducing variance. Methods for reducing neural network complexity can be viewed as a regularization technique to reduce this variance. Examples of such methods are Optimal Brain Damage (Le Cun et.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found