Learning Through Concepts: Hierarchies, Logic and Reasoning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41092-41093
DOI: 10.1609/aaai.v40i48.42172 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Deepika SN Vemuri.
Abstract (Originalsprache)
This thesis aims to bridge the gap between data-driven models and symbolic learning through the lens of Concept-Based Learning, a paradigm that guides model learning through high-level, human-understandable concepts. Here, models first learn a set of concepts, subsequently using them to perform a task of interest. Prior work on concept-based models has largely focused on relatively simple classification settings, where classes are linear combinations of pre-specified concepts; treating concepts largely as tools to increase interpretability, rather than as fundamental building blocks of the learning process itself. In contrast, this thesis explores the broader potential of concepts, as the core units of representation and reasoning in neural network models, capable of shaping how models learn and generalize.
Zitieren
APA
Vemuri, D. S. (2026). Learning Through Concepts: Hierarchies, Logic and Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41092-41093. https://doi.org/10.1609/aaai.v40i48.42172
Vancouver
Vemuri DS. Learning Through Concepts: Hierarchies, Logic and Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41092-41093. doi:10.1609/aaai.v40i48.42172
BibTeX
@article{Vemuri2026,
author = {Vemuri, Deepika SN},
title = {Learning Through Concepts: Hierarchies, Logic and Reasoning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41092--41093},
doi = {10.1609/aaai.v40i48.42172}
}
EUVIMED