Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Zhang, Yihao
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.20161
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914992292364288
author Zhang, Yihao
author_facet Zhang, Yihao
contents The pursuit of interpretable artificial intelligence has led to significant advancements in the development of methods that aim to explain the decision-making processes of complex models, such as deep learning systems. Among these methods, causal abstraction stands out as a theoretical framework that provides a principled approach to understanding and explaining the causal mechanisms underlying model behavior. This survey paper delves into the realm of causal abstraction, examining its theoretical foundations, practical applications, and implications for the field of model interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20161
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Causal Abstraction in Model Interpretability: A Compact Survey
Zhang, Yihao
Machine Learning
Artificial Intelligence
Computation and Language
The pursuit of interpretable artificial intelligence has led to significant advancements in the development of methods that aim to explain the decision-making processes of complex models, such as deep learning systems. Among these methods, causal abstraction stands out as a theoretical framework that provides a principled approach to understanding and explaining the causal mechanisms underlying model behavior. This survey paper delves into the realm of causal abstraction, examining its theoretical foundations, practical applications, and implications for the field of model interpretability.
title Causal Abstraction in Model Interpretability: A Compact Survey
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2410.20161