Metraipolis › archive › dc_e305f660441f
AIBL: Augmented Instance-Based Learning with Structured Memory and Neural Embeddings — arXiv:2610.03413
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03413
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:17.164Z
- SHA-256 of the archived text
c237841993d969afd3f416067dffa9d40a16bcf87c98db787e401e3b4649b8a7- Stable URL of this page
https://metraipolis.com/documento/dc_e305f660441f
How to cite
AIBL: Augmented Instance-Based Learning with Structured Memory and Neural Embeddings — arXiv:2610.03413 — arXiv, https://arxiv.org/abs/2610.03413 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e305f660441f (Metraipolis archive dc_e305f660441f, sha256 c237841993d969afd3f416067dffa9d40a16bcf87c98db787e401e3b4649b8a7)
BibTeX
@misc{dce305f660441f,
title = {AIBL: Augmented Instance-Based Learning with Structured Memory and Neural Embeddings — arXiv:2610.03413},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03413},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e305f660441f; sha256 c237841993d969afd3f416067dffa9d40a16bcf87c98db787e401e3b4649b8a7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03413. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sequential learning systems often make decisions from accumulated experience while receiving high-dimensional inputs whose distribution may change over time. Instance-Based Learning Theory (IBLT) provides a principled case-based framework for such settings through stored situation-decision-utility instances, partial matching, activation, and blending. IBLT relies on symbolic knowledge representation in dictionary-like formats, but text, images, transaction vectors, and user-item histories often require learned similarity rather than hand-specified matching rules. In this paper, we introduce AIBL (Augmented Instance-Based Learning), an instance-learning model formulated in a learned vector space for high- dimensional sequential data. AIBL generalizes symbolic situation matching to neural embedding similarity while retaining instance storage, activation- weighted retrieval, and utility blending. The AIBL model organizes memory into active, forgotten, and surprise stores. Surprise memory separates weakly matched, possible out-of-distribution, or corner-case observations from active memory, reducing forced fitting to the nearest available cases. An observation-driven graduation algorithm promotes recurring surprise instances to active memory, allowing the memory to incorporate repeated novel patterns that may arise under concept drift. We evaluate the same implementation on five machine learning tasks and three controlled simulation tasks, comparing AIBL with classical IBLT variants and task-specific baselines where appropriate. AIBL improves accuracy by 6 to 17 percentage points. The results show where vector-space retrieval improves over symbolic matching and how the added memory mechanisms govern novelty detection, cold-start handling, drift adaptation, and reward learning under the tested protocols. 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/2610.03413 — 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 2026-10-05T23:01:38.693Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).