Explainable deep learning: a field guide for the uninitiated

DOI10.1613/JAIR.1.13200MaRDI QIDQ5026262zbMATH OpenOpenAlexFDO

Authors Gabrielle Ras, Ning Xie, Derek Doran, M. A. J. Van Gerven

Publication date 7 February 2022

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2004.14545

zbMATH Keywords

machine learningneural networks

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• A survey on the explainability of supervised machine learning
• Definitions, methods, and applications in interpretable machine learning
• Understanding Deep Learning with Statistical Relevance
• Interpretability in Deep Learning
• Explanation in artificial intelligence: insights from the social sciences

Cites work

• Classification using class cover catch digraphs
• Explaining AI decisions using efficient methods for learning sparse Boolean formulae
• Explanation in artificial intelligence: insights from the social sciences
• Fairness through awareness
• Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates
• How to explain individual classification decisions
• scientific article; zbMATH DE number 1911276 (Why is no real title available?)
• scientific article; zbMATH DE number 3078997 (Why is no real title available?)
• Prototype selection for interpretable classification

Cited in

(17)

• Explicative deep learning with probabilistic formal concepts in a natural language processing task
• Explanation in AI and law: past, present and future
• Beneficial and harmful explanatory machine learning
• Explanation in artificial intelligence: insights from the social sciences
• Explaining explanations: axiomatic feature interactions for deep networks
• On Tackling Explanation Redundancy in Decision Trees
• Objective Bayesian Nets for Integrating Consistent Datasets
• A survey on the explainability of supervised machine learning
• Explaining the Decisions of Convolutional and Recurrent Neural Networks
• Logical perspectives on the foundations of probability
• The explanation game: a formal framework for interpretable machine learning
• Explainable generalized additive neural networks with independent neural network training
• Efficient computation of shap explanation scores for neural network classifiers via knowledge compilation
• Identifying highly relevant entries in datasets: a relevance-based classification
• Efficient XAI: a low-cost data reduction approach to SHAP interpretability
• Computability of classification and deep learning: from theoretical limits to practical feasibility through quantization
• Mathematical algorithm design for deep learning under societal and judicial constraints: the algorithmic transparency requirement

Describes a project that uses

Uses Software

• CLEVR
• GPT-3
• MagNet
• PyTorch
• Tensor2Tensor
• BERT
• shap
• CLEVR dataset
• Grad-CAM
• SVCCA
• VQA
• Adv-BNN

This page was built for publication: Explainable deep learning: a field guide for the uninitiated

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5026262)