A Critical Review of Inductive Logic Programming Techniques for Explainable AI

Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption. To instill confidence and trust in artificial intelligence (AI) systems, explainable AI (XAI) has emerged as a response to improve modern machine lear...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transaction on neural networks and learning systems Ročník 35; číslo 8; s. 10220 - 10236
Hlavní autoři: Zhang, Zheng, Yilmaz, Levent, Liu, Bo
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.08.2024
Témata:
Artificial intelligence
Differentiable inductive logic programming (∂ILP)
explainable artificial intelligence (XAI)
Flowcharts
ILP
Learning systems
Logic programming
machine learning
meta-interpretive learning (MIL)
neuro-symbolic AI
Pipelines
probabilistic ILP (PILP)
Semantics
statistical relational learning (SRL)
Task analysis
ISSN:2162-237X, 2162-2388, 2162-2388
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption. To instill confidence and trust in artificial intelligence (AI) systems, explainable AI (XAI) has emerged as a response to improve modern machine learning algorithms' explainability. Inductive logic programming (ILP), a subfield of symbolic AI, plays a promising role in generating interpretable explanations because of its intuitive logic-driven framework. ILP effectively leverages abductive reasoning to generate explainable first-order clausal theories from examples and background knowledge. However, several challenges in developing methods inspired by ILP need to be addressed for their successful application in practice. For example, the existing ILP systems often have a vast solution space, and the induced solutions are very sensitive to noises and disturbances. This survey paper summarizes the recent advances in ILP and a discussion of statistical relational learning (SRL) and neural-symbolic algorithms, which offer synergistic views to ILP. Following a critical review of the recent advances, we delineate observed challenges and highlight potential avenues of further ILP-motivated research toward developing self-explanatory AI systems.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2023.3246980