Searching for "Hypothesis Spaces for Learning." – sorted by Relevance.
-
Learning Internal Representations
- the most important problem in machine learning is the preliminary biasing of a learner's hypothesis space
- Cited by 72 (8 self) – Add To MetaCart
-
A Theory Of Learning Classification Rules
- three components: the hypothesis space, the learning protocol, and criteria for successful learning
- Cited by 74 (6 self) – Add To MetaCart
-
"Practical" PAC Analyses of Instance-Based Learning Algorithms
- ffi + log jH L C j ffl ), where H L C is the hypothesis space of the learning algorithm L w
- Add To MetaCart
-
Detecting Interesting Instances
- , the hypothesis space is enlarged in order to characterize local patterns in a second learning step. 1
- Add To MetaCart
-
HYDRA-MM: learning multiple descriptions to improve classification accuracy
- are particularly helpful for improving accuracy in hypothesis spaces in which there are many equally good rules
- Cited by 8 (2 self) – Add To MetaCart
-
On learning multiple descriptions of a concept
- over all possible hypotheses in the hypothesis space of the learning algorithm. In practice, we only
- Cited by 9 (1 self) – Add To MetaCart
-
Detecting Interesting Instances
- . This structure of the hypothesis space is used while doing top-down search for learning. If a rule is learned its
- Cited by 6 (2 self) – Add To MetaCart
-
Learning Long-Distance Agreement Phonotactics
- -Distance Agreement Phonotactics Jeff Heinz Inductive Learning and the Hypothesis Space • Learning cannot take place
- Add To MetaCart
-
Text Categorization with Support Vector Machines: Learning with Many Relevant Features
- .1 Non-linear Hypothesis Spaces To learn nonlinear hypotheses, SVMs make use of convolution functions K
- Cited by 1055 (10 self) – Add To MetaCart
-
A Formalization of Explanation-Based Macro-operator Learning
- . We show that when a domain and the hypothesis space of the learning system satisfy these biases
- Cited by 12 (3 self) – Add To MetaCart

