180 search results - page 17 / 36 » Improved bounds on the sample complexity of learning |
CGF
1999
13 years 7 months ago
1999
This paper describes the successful combination of pre-generated and dynamically updated image-based representations to accelerate the visualization of complex virtual environment...
FOCS
2003
IEEE
14 years 25 days ago
2003
IEEE
We give a surprisingly short proof that in any planar arrangement of Ò curves where each pair intersects at most a fixed number (×) of times, the -level has subquadratic (Ç´...
IJPRAI
2002
13 years 7 months ago
2002
Decision-tree algorithms are known to be unstable: small variations in the training set can result in different trees and different predictions for the same validation examples. B...
CEC
2010
IEEE
13 years 8 months ago
2010
IEEE
This paper presents a novel hybrid method combining genetic programming and decision tree learning. The method starts by estimating a benchmark level of reasonable accuracy, based ...
NIPS
2001
13 years 9 months ago
2001
Classical statistical learning theory studies the generalisation performance of machine learning algorithms rather indirectly. One of the main detours is that algorithms are studi...