Incremental Learning with Ordinal Bounded Example Memory
Abstract
A Bounded Example Memory learner is a learner that operates incrementally and maintains a memory of finitely many data items. The paradigm is well-studied and known to coincide with set-driven learning. A hierarchy of stronger and stronger learning criteria is obtained when one considers, for each k ∈ N , iterative learners that can maintain a memory of at most k previously processed data items. We report on recent investigations of extensions of the Bounded Example Memory model where a constructive ordinal notation is used to bound the number of times the learner can ask for proper global memory extensions.
Cite
Text
Carlucci. "Incremental Learning with Ordinal Bounded Example Memory." International Conference on Algorithmic Learning Theory, 2009. doi:10.1007/978-3-642-04414-4_27Markdown
[Carlucci. "Incremental Learning with Ordinal Bounded Example Memory." International Conference on Algorithmic Learning Theory, 2009.](https://mlanthology.org/alt/2009/carlucci2009alt-incremental/) doi:10.1007/978-3-642-04414-4_27BibTeX
@inproceedings{carlucci2009alt-incremental,
title = {{Incremental Learning with Ordinal Bounded Example Memory}},
author = {Carlucci, Lorenzo},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {2009},
pages = {323-337},
doi = {10.1007/978-3-642-04414-4_27},
url = {https://mlanthology.org/alt/2009/carlucci2009alt-incremental/}
}