Two New Frameworks for Learning
Abstract
This paper presents two new formal frameworks for learning. The first framework requires the learner to approximate an unknown function, given examples for the function as well as some background information on it. As far as information complexity is concerned, it is shown that this framework is no more powerful than a framework that allows the learner to see examples but not background information. The second framework explores learning in the sense of improving computational efficiency as opposed to acquiring an unknown concept or function. Specifically, the framework concerns the acquisition of heuristics over problem domains of special structure. A theorem is proved identifying some conditions sufficient to allow the efficient acquisition of heuristics over the aforementioned class of domains. The framework is illustrated with the help of an implemented program in the domain of symbolic integration.
Cite
Text
Natarajan and Tadepalli. "Two New Frameworks for Learning." International Conference on Machine Learning, 1988. doi:10.1016/B978-0-934613-64-4.50046-3Markdown
[Natarajan and Tadepalli. "Two New Frameworks for Learning." International Conference on Machine Learning, 1988.](https://mlanthology.org/icml/1988/natarajan1988icml-two/) doi:10.1016/B978-0-934613-64-4.50046-3BibTeX
@inproceedings{natarajan1988icml-two,
title = {{Two New Frameworks for Learning}},
author = {Natarajan, Balas K. and Tadepalli, Prasad},
booktitle = {International Conference on Machine Learning},
year = {1988},
pages = {402-415},
doi = {10.1016/B978-0-934613-64-4.50046-3},
url = {https://mlanthology.org/icml/1988/natarajan1988icml-two/}
}