Metraipolis › archive › dc_68ad7e8dff41
Quantifying the Value of Constructive Induction, Knowledge, and Noise Filtering on Inductive Learning — arXiv:2610.02615
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02615
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:09:42.455Z
- SHA-256 of the archived text
21a8c55a07abf1792d30c01eeb7602f76e133bb995eec8ab96d9c9564a5173fc- Stable URL of this page
https://metraipolis.com/documento/dc_68ad7e8dff41
How to cite
Quantifying the Value of Constructive Induction, Knowledge, and Noise Filtering on Inductive Learning — arXiv:2610.02615 — arXiv, https://arxiv.org/abs/2610.02615 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_68ad7e8dff41 (Metraipolis archive dc_68ad7e8dff41, sha256 21a8c55a07abf1792d30c01eeb7602f76e133bb995eec8ab96d9c9564a5173fc)
BibTeX
@misc{dc68ad7e8dff41,
title = {Quantifying the Value of Constructive Induction, Knowledge, and Noise Filtering on Inductive Learning — arXiv:2610.02615},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02615},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_68ad7e8dff41; sha256 21a8c55a07abf1792d30c01eeb7602f76e133bb995eec8ab96d9c9564a5173fc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02615. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learning research, as one of its central goals, tries to measure, model, and understand how learning-problem properties affect average-case learning performance. For example, we would like to quantify the value of constructive induction, noise filtering, and background knowledge. This paper describes the effective dimension, a new learning measure that helps link problem properties to learning performance. Like the Vapnik-Chervonenkis (VC) dimension, the effective dimension is often in a simple linear relation with problem properties. Unlike the VC dimension, the effective dimension can be estimated empirically and makes average-case predictions. It is therefore more widely applicable to machine and human learning research. The measure is demonstrated on several learning systems including Backpropagation. Finally, the measure is used to precisely predict the benefit of using FRINGE, a feature construction system. The benefit is found to decrease as the complexity of the target concept increases. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.02615 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-05T23:01:38.613Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).