The Logic of Hebbian Learning

We present the logic of Hebbian learning, a dynamic logicwhose semantics1 are expressed in terms of a layered neuralnetwork learning via Hebb’s associative learning rule. Its lan-guage consists of modality Tφ (read “typically φ,” formalizedas forward propagation), conditionals φ ⇒ ψ (read “typi-call...

Full description

Saved in:
Bibliographic Details
Main Authors: Caleb Kisby, Saúl Blanco, Lawrence Moss
Format: Article
Language:English
Published: LibraryPress@UF 2022-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/130735
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850271247218245632
author Caleb Kisby
Saúl Blanco
Lawrence Moss
author_facet Caleb Kisby
Saúl Blanco
Lawrence Moss
author_sort Caleb Kisby
collection DOAJ
description We present the logic of Hebbian learning, a dynamic logicwhose semantics1 are expressed in terms of a layered neuralnetwork learning via Hebb’s associative learning rule. Its lan-guage consists of modality Tφ (read “typically φ,” formalizedas forward propagation), conditionals φ ⇒ ψ (read “typi-cally φ are ψ”), as well as dynamic modalities [φ+]ψ (read“evaluate ψ after performing Hebbian update on φ”). We giveaxioms and inference rules that are sound with respect to theneural semantics; these axioms characterize Hebbian learningand its interaction with propagation. The upshot is that thislogic describes a neuro-symbolic agent that both learns fromexperience and also reasons about what it has learned.
format Article
id doaj-art-20d63dcb4e364d0fb7b35c324b480cbe
institution OA Journals
issn 2334-0754
2334-0762
language English
publishDate 2022-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-20d63dcb4e364d0fb7b35c324b480cbe2025-08-20T01:52:18ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622022-05-013510.32473/flairs.v35i.13073566934The Logic of Hebbian LearningCaleb Kisby0Saúl Blanco1Lawrence Moss2Department of Computer Science, Indiana University BloomingtonDepartment of Computer Science, Indiana University BloomingtonDepartment of Mathematics, Indiana University BloomingtonWe present the logic of Hebbian learning, a dynamic logicwhose semantics1 are expressed in terms of a layered neuralnetwork learning via Hebb’s associative learning rule. Its lan-guage consists of modality Tφ (read “typically φ,” formalizedas forward propagation), conditionals φ ⇒ ψ (read “typi-cally φ are ψ”), as well as dynamic modalities [φ+]ψ (read“evaluate ψ after performing Hebbian update on φ”). We giveaxioms and inference rules that are sound with respect to theneural semantics; these axioms characterize Hebbian learningand its interaction with propagation. The upshot is that thislogic describes a neuro-symbolic agent that both learns fromexperience and also reasons about what it has learned.https://journals.flvc.org/FLAIRS/article/view/130735neurosymbolic aihebbian learningdynamic logicsknowledge representation and reasoningnonmonotonic reasoningpreference upgrade
spellingShingle Caleb Kisby
Saúl Blanco
Lawrence Moss
The Logic of Hebbian Learning
Proceedings of the International Florida Artificial Intelligence Research Society Conference
neurosymbolic ai
hebbian learning
dynamic logics
knowledge representation and reasoning
nonmonotonic reasoning
preference upgrade
title The Logic of Hebbian Learning
title_full The Logic of Hebbian Learning
title_fullStr The Logic of Hebbian Learning
title_full_unstemmed The Logic of Hebbian Learning
title_short The Logic of Hebbian Learning
title_sort logic of hebbian learning
topic neurosymbolic ai
hebbian learning
dynamic logics
knowledge representation and reasoning
nonmonotonic reasoning
preference upgrade
url https://journals.flvc.org/FLAIRS/article/view/130735
work_keys_str_mv AT calebkisby thelogicofhebbianlearning
AT saulblanco thelogicofhebbianlearning
AT lawrencemoss thelogicofhebbianlearning
AT calebkisby logicofhebbianlearning
AT saulblanco logicofhebbianlearning
AT lawrencemoss logicofhebbianlearning