From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lee, Jae Hee, Lanza, Sergio, Wermter, Stefan
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911863986454528
author Lee, Jae Hee
Lanza, Sergio
Wermter, Stefan
author_facet Lee, Jae Hee
Lanza, Sergio
Wermter, Stefan
contents In this paper, we review recent approaches for explaining concepts in neural networks. Concepts can act as a natural link between learning and reasoning: once the concepts are identified that a neural learning system uses, one can integrate those concepts with a reasoning system for inference or use a reasoning system to act upon them to improve or enhance the learning system. On the other hand, knowledge can not only be extracted from neural networks but concept knowledge can also be inserted into neural network architectures. Since integrating learning and reasoning is at the core of neuro-symbolic AI, the insights gained from this survey can serve as an important step towards realizing neuro-symbolic AI based on explainable concepts.
format Preprint
id arxiv_https___arxiv_org_abs_2310_11884
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks
Lee, Jae Hee
Lanza, Sergio
Wermter, Stefan
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
In this paper, we review recent approaches for explaining concepts in neural networks. Concepts can act as a natural link between learning and reasoning: once the concepts are identified that a neural learning system uses, one can integrate those concepts with a reasoning system for inference or use a reasoning system to act upon them to improve or enhance the learning system. On the other hand, knowledge can not only be extracted from neural networks but concept knowledge can also be inserted into neural network architectures. Since integrating learning and reasoning is at the core of neuro-symbolic AI, the insights gained from this survey can serve as an important step towards realizing neuro-symbolic AI based on explainable concepts.
title From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks
topic Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2310.11884