636 search results - page 60 / 128 » Measuring Complexity of Intelligent Machines |
ECML
2006
Springer
15 years 1 months ago
2006
Springer
Multiple-instance learning (MIL) is a popular concept among the AI community to support supervised learning applications in situations where only incomplete knowledge is available....
IPL
2002
14 years 9 months ago
2002
One of the main reasons for using parallel evolutionary algorithms (PEAs) is to obtain efficient algorithms with an execution time much lower than that of their sequential counter...
ALT
2006
Springer
15 years 6 months ago
2006
Springer
Most of the existing active learning algorithms are based on the realizability assumption: The learner’s hypothesis class is assumed to contain a target function that perfectly c...
ICML
2004
IEEE
15 years 10 months ago
2004
IEEE
We propose a simple, novel and yet effective method for building and testing decision trees that minimizes the sum of the misclassification and test costs. More specifically, we f...
113
click to vote
EMNLP
2010
14 years 7 months ago
2010
Extant Statistical Machine Translation (SMT) systems are very complex softwares, which embed multiple layers of heuristics and embark very large numbers of numerical parameters. A...