INTERPRETABILITY, EXPLAINABILITY AND CAUSALITY IN DEEP LEARNING
RCHUB JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE) · 2025
DOI: 10.65725/jcise/1/2/001 ↗Kurz gefasst
Fachartikel in der Zeitschrift RCHUB JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE), 2025. Verfasst von Seshaiah Merikapudi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref).
Abstract (Originalsprache)
Despite revolutionizing sectors like medicine, finance, natural language processing, and autonomous technologies, the intricate and non-transparent designs of deep learning architectures restrict confidence and clarity. Existing post-hoc explanation methods (e.g., saliency maps, SHAP, and counterfactuals) yield insights that are often incomplete and inconsistent, frequently uncovering statistical correlations instead of definitive causal factors. Consequently, establishing interpretability and causality is now crucial for successfully deploying AI in critical applications. Causal inference provides a more solid framework by identifying authentic cause-and-effect relationships and boosting model reliability when data distributions change. Nevertheless, incorporating robust causal structures into neural networks is challenging due to data availability and high computational demands. This paper examines prominent interpretability and causal methodologies, discusses their drawbacks, and proposes future research avenues aimed at engineering deep learning models that are simultaneously precise, transparent, and trustworthy
Zitieren
APA
Merikapudi, S., C, C. T., A, A., & S, A. F. A. D. (2025). INTERPRETABILITY, EXPLAINABILITY AND CAUSALITY IN DEEP LEARNING. RCHUB JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE). https://doi.org/10.65725/jcise/1/2/001
Vancouver
Merikapudi S, C CT, A A, S AFAD. INTERPRETABILITY, EXPLAINABILITY AND CAUSALITY IN DEEP LEARNING. RCHUB JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE). 2025. doi:10.65725/jcise/1/2/001
BibTeX
@article{Merikapudi2025,
author = {Merikapudi, Seshaiah and C, Chinmyi T and A, Amulya and S, Aqsa Firdose and Deeksha},
title = {INTERPRETABILITY, EXPLAINABILITY AND CAUSALITY IN DEEP LEARNING},
journal = {RCHUB JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE)},
year = {2025},
doi = {10.65725/jcise/1/2/001}
}
EUVIMED