Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks

Paul Ardis, Arjuna Flenner
3/13/2024
cs.LGstat.ML

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Deep Neural Networks (DNNs) do not inherently compute or exhibit empirically-justified task confidence. In mission critical applications, it is important to both understand associated DNN reasoning and its supporting evidence. In this paper, we propose a novel Bayesian approach to extract explanations, justifications, and uncertainty estimates from DNNs. Our approach is efficient both in terms of memory and computation, and can be applied to any black box DNN without any retraining, including applications to anomaly detection and out-of-distribution detection tasks. We validate our approach on the CIFAR-10 dataset, and show that it can significantly improve the interpretability and reliability of DNNs.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Uncertainty Quantification for Gradient-based Explanations in Neural Networks

85% match2024

Multidimensional Uncertainty Quantification for Deep Neural Networks

84% match2023

Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks

83% match2025

Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Prediction

83% match2024

Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning

82% match2024

Uncertainty Quantification in Deep Neural Networks through Statistical Inference on Latent Space

81% match2023

Cite this paper

@article{ardis2024extracting,
  title  = {Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks},
  author = {Paul Ardis and Arjuna Flenner},
  year   = {2024},
  eprint = {2403.08652},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.08652v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.08652.svg)](https://codeofpaper.com/paper/2403.08652)

Discussion