Spectral zones based SHAP: enhancing interpretability in spectral deep learning models

Jhonatan Contreras; Thomas Bocklitz

doi:10.1117/12.3016969

19 June 2024 Spectral zones based SHAP: enhancing interpretability in spectral deep learning models

Jhonatan Contreras, Thomas Bocklitz

Author Affiliations +

Proceedings Volume PC13011, Data Science for Photonics and Biophotonics; PC130110A (2024) https://doi.org/10.1117/12.3016969
Event: SPIE Photonics Europe, 2024, Strasbourg, France

Abstract

Deep learning models are widely used because of their high accuracy in solving classification problems in spectroscopy, but they lack interpretability. The challenge lies in the balance between interpretability and accuracy. Current interpretive methods, such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), can sometimes provide mathematical meaning but physically implausible interpretations by perturbing individual feature values. To address this gap, our research proposes a group-focused methodology that targets 'spectral zones' to estimate the impact of collective spectral features directly. This approach enhances the interpretability of deep learning models, diminishes noisy data, and provides a more comprehensive understanding of model behaviors. By applying group perturbations, the resultant interpretations are not only more intuitive but also offer results that are easily comparable with domain expertise, thus leading to an enriched analysis of the model's decision-making processes.

Conference Presentation

Citation Download Citation

Jhonatan Contreras and Thomas Bocklitz "Spectral zones based SHAP: enhancing interpretability in spectral deep learning models", Proc. SPIE PC13011, Data Science for Photonics and Biophotonics, PC130110A (19 June 2024); https://doi.org/10.1117/12.3016969

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE