Record:   Prev Next
作者 Langford, John
書名 Quantitatively tight sample complexity bounds
國際標準書號 9780542015564
book jacket
說明 130 p
附註 Source: Dissertation Abstracts International, Volume: 66-02, Section: B, page: 0989
Co-Chairs: Avrim Blum; Sebastian Thrun
Thesis (Ph.D.)--Carnegie Mellon University, 2002
I present many new results on sample complexity bounds (bounds on the future error rate of arbitrary learning algorithms). Of theoretical interest are qualitative and quantitative improvements in sample complexity bounds as well as some techniques and criteria for judging the tightness of sample complexity bounds
On the practical side, I show quantitative results (with true error rate bounds sometimes less than 0.01) for decision trees and neural networks with these sample complexity bounds applied to real world problems. I also present a technique for using both sample complexity bounds and (more traditional) holdout techniques
Together, the theoretical and practical results of this thesis provide a well-founded practical method for evaluating learning algorithm performance based upon both training and testing set performance
Code for calculating these bounds is provided
School code: 0041
DDC
Host Item Dissertation Abstracts International 66-02B
主題 Mathematics
Computer Science
0405
0984
Alt Author Carnegie Mellon University
Record:   Prev Next