Towards a Better Understanding of Incremental Learning
Abstract
The present study aims at insights into the nature of incremental learning in the context of Gold’s model of identification in the limit. With a focus on natural requirements such as consistency and conservativeness, incremental learning is analysed both for learning from positive examples and for learning from positive and negative examples. The results obtained illustrate in which way different consistency and conservativeness demands can affect the capabilities of incremental learners. These results may serve as a first step towards characterising the structure of typical classes learnable incrementally and thus towards elaborating uniform incremental learning methods.
Cite
Text
Jain et al. "Towards a Better Understanding of Incremental Learning." International Conference on Algorithmic Learning Theory, 2006. doi:10.1007/11894841_16Markdown
[Jain et al. "Towards a Better Understanding of Incremental Learning." International Conference on Algorithmic Learning Theory, 2006.](https://mlanthology.org/alt/2006/jain2006alt-better/) doi:10.1007/11894841_16BibTeX
@inproceedings{jain2006alt-better,
title = {{Towards a Better Understanding of Incremental Learning}},
author = {Jain, Sanjay and Lange, Steffen and Zilles, Sandra},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {2006},
pages = {169-183},
doi = {10.1007/11894841_16},
url = {https://mlanthology.org/alt/2006/jain2006alt-better/}
}