EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Propagating Transparency: A Deep Dive into the Interpretability of Neural Networks

Ayush Somani, Alexander Horsch, Ajit Bopardikar, Dilip K. Prasad

Nordic Machine Intelligence · 2024

DOI: 10.5617/nmi.10755 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nordic Machine Intelligence, 2024. Verfasst von Ayush Somani und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the rapidly evolving landscape of deep learning (DL), understanding the inner workings of neural networks remains a significant challenge. This need for transparency and accountability from DL models assumes particular importance as DL models become increasingly prevalent in decision-making processes. Interpreting these models is key to addressing this challenge. This paper offers a comprehensive overview of interpretable deep learning methods. It emphasizes gradient-based propagation techniques that shed light on the complex mechanisms driving neural network predictions. Through a systematic review, we categorize gradient-based interpretability approaches, delve into the theory of notable methods, and compare their strengths and weaknesses. Furthermore, we investigate various evaluation metrics for interpretable systems, often generalized under the term eXplainable Artificial Intelligence (XAI). We highlight their significance in assessing the faithfulness, robustness, localization, complexity, randomization, and adherence to the axiomatic principles of XAI methods. We aim to help researchers and practitioners work towards a more transparent future for artificial intelligence by providing an overview of the most recent developments in the field.

Zitieren

APA

Somani, A., Horsch, A., Bopardikar, A., & Prasad, D. K. (2024). Propagating Transparency: A Deep Dive into the Interpretability of Neural Networks. Nordic Machine Intelligence. https://doi.org/10.5617/nmi.10755

Vancouver

Somani A, Horsch A, Bopardikar A, Prasad DK. Propagating Transparency: A Deep Dive into the Interpretability of Neural Networks. Nordic Machine Intelligence. 2024. doi:10.5617/nmi.10755

BibTeX
@article{Somani2024,
  author = {Somani, Ayush and Horsch, Alexander and Bopardikar, Ajit and Prasad, Dilip K.},
  title = {Propagating Transparency: A Deep Dive into the Interpretability of Neural Networks},
  journal = {Nordic Machine Intelligence},
  year = {2024},
  doi = {10.5617/nmi.10755}
}
Kostenlos starten →