7928 search results - page 279 / 1586 » Human-Like Learning Methods for a |
172
click to vote
CGO
2009
IEEE
16 years 1 months ago
2009
IEEE
Recent work has shown that machine learning can automate and in some cases outperform hand crafted compiler optimizations. Central to such an approach is that machine learning tec...
142
click to vote
CCS
2009
ACM
16 years 1 months ago
2009
ACM
We propose a framework for quantitative security analysis of machine learning methods. Key issus of this framework are a formal specification of the deployed learning model and a...
161
click to vote
ECML
2007
Springer
16 years 13 days ago
2007
Springer
Decision tree learning algorithms produce accurate models that can be interpreted by domain experts. However, these algorithms are known to be unstable – they can produce drastic...
157
click to vote
IJCNN
2006
IEEE
16 years 8 days ago
2006
IEEE
Abstract— Over the years, many improvements and refinements of the backpropagation learning algorithm have been reported. In this paper, a new adaptive penalty-based learning ex...
163
click to vote
KDD
2004
ACM
16 years 6 months ago
2004
ACM
Past empirical work has shown that learning multiple related tasks from data simultaneously can be advantageous in terms of predictive performance relative to learning these tasks...