Beyond the Black Box: A Hybrid SHAP-LIME Approach for Transparent and Explainable Deep Neural Networks

Abstract

Deep Neural Networks (DNNs) have been successfully used in various fields, nonetheless their lack of clarity poses serious issues in trust, interpretability, and responsibility in critical areas such as healthcare. In this paper, we propose a new hybrid approach of explainability by combining SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanations (LIME) towards improving the interpretability of deep learning models. SHAP offers a global feature importance, which gives a wide-ranging perspective on model behavior while LIME provides local instance-based explanations that clarify individual predictions. Our hybrid approach of SHAP and LIME combines both techniques to improve understanding of model decision making. We evaluated our method with two case studies including Handwritten Digit Recognition (MNIST) and Alzheimer’s disease detection. The experimental results demonstrated that the hybrid approach improved accuracy by $97.92 \%$, increased trust in Al powered decision making, and outperformed other standalone explainability methods in local and global interpretability. The work presented in this document deepens the research on explainable AI (XAI) by proposing a meaningful and straightforward approach that is generally applicable to deep learning systems.

Ähnliche Arbeiten