Empirical Investigation of the Effect of Pruning Artificial Neural Networks With Respect to Increased Generalization Ability
Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
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.
Place, publisher, year, edition, pages
2010. , 53 p.
Artifical Neural Networks, Pruning, Empirical Investigation, Proben1, Magnitude Based Pruning, Optimal Brain Damage, Optimal Brain Surgeon
IdentifiersURN: urn:nbn:se:liu:diva-60112ISRN: LIU-IDA/LITH-EX-A--10/018--SEOAI: oai:DiVA.org:liu-60112DiVA: diva2:355145