Return to search

Empirical Investigation of the Effect of Pruning Artificial Neural Networks With Respect to Increased Generalization Ability

This final thesis covers the basics of artificial neural networks, with focus on supervised learning, pruning and the problem of achieving good generalization ability. An empirical investigation is conducted on twelve dierent problems originating from the Proben1 benchmark collection.The results indicate that pruning is more likely to improve generalization if the data is sensitive to overtting or if the networks are likely to be trapped in local minima.

Identiferoai:union.ndltd.org:UPSALLA1/oai:DiVA.org:liu-60112
Date January 2010
CreatorsWeman, Nicklas
PublisherLinköpings universitet, Institutionen för datavetenskap
Source SetsDiVA Archive at Upsalla University
LanguageEnglish
Detected LanguageEnglish
TypeStudent thesis, info:eu-repo/semantics/masterThesis, text
Formatapplication/pdf
Rightsinfo:eu-repo/semantics/openAccess

Page generated in 0.002 seconds