Learning by Switching Type of Information
Abstract
The present work is dedicated to the study of modes of datapresentation between text and informant within the framework of inductive inference. The model is such that the learner requests sequences of positive andnegativ e data andthe relations between the various formalizations in dependence on the number of switches between positive and negative data is investigated. In particular it is shown that there is a proper hierarchy of the notions of learning from standard text, in the basic switching model, in the newtext switching model and in the restart switching model. The last one of these turns out to be equivalent to the standard notion of learning from informant.
Cite
Text
Jain and Stephan. "Learning by Switching Type of Information." International Conference on Algorithmic Learning Theory, 2001. doi:10.1007/3-540-45583-3_17Markdown
[Jain and Stephan. "Learning by Switching Type of Information." International Conference on Algorithmic Learning Theory, 2001.](https://mlanthology.org/alt/2001/jain2001alt-learning-b/) doi:10.1007/3-540-45583-3_17BibTeX
@inproceedings{jain2001alt-learning-b,
title = {{Learning by Switching Type of Information}},
author = {Jain, Sanjay and Stephan, Frank},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {2001},
pages = {205-218},
doi = {10.1007/3-540-45583-3_17},
url = {https://mlanthology.org/alt/2001/jain2001alt-learning-b/}
}