Explaining Deep Learning Models - A Bayesian Non-parametric Approach

Abstract

Understanding and interpreting how machine learning (ML) models make decisions have been a big challenge. While recent research has proposed various technical approaches to provide some clues as to how an ML model makes individual predictions, they cannot provide users with an ability to inspect a model as a complete entity. In this work, we propose a novel technical approach that augments a Bayesian non-parametric regression mixture model with multiple elastic nets. Using the enhanced mixture model, we can extract generalizable insights for a target model through a global approximation. To demonstrate the utility of our approach, we evaluate it on different ML models in the context of image recognition. The empirical results indicate that our proposed approach not only outperforms the state-of-the-art techniques in explaining individual decisions but also provides users with an ability to discover the vulnerabilities of the target ML models.

arXiv commentIn Proceedings of the 32nd Conference on Neural Information Processing Systems. arXiv admin note: text overlap with arXiv:1705.08564

Cited by in corpus (13)

• TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
• A Survey on Graph-Based Deep Learning for Computational Histopathology
• BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations
• Reliable Post hoc Explanations: Modeling Uncertainty in Explainability
• Generative causal explanations of black-box classifiers
• Mixture of Linear Models Co-supervised by Deep Neural Networks
• A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks
• TSInsight: A local-global attribution framework for interpretability in time-series data
• Exact and Consistent Interpretation of Piecewise Linear Models Hidden behind APIs: A Closed Form Solution
• Bayesian Nonparametric Modelling for Model-Free Reinforcement Learning in LTE-LAA and Wi-Fi Coexistence
• Bayesian Nonparametric Reinforcement Learning in LTE and Wi-Fi Coexistence
• Automated Dependence Plots
• Interpretability of Blackbox Machine Learning Models through Dataview Extraction and Shadow Model creation