Explaining black-box classifiers using post-hoc explanations-by-example: The effect of explanations and error-rates in XAI user studies
177
TL;DR: A post-hoc explanation-by-example approach to eXplainable AI (XAI), where a black-box, deep learning system is explained by reference to a more transparent, proxy model based on a feature-weighting analysis of the former that is used to find explanatory cases from the latter (as one instance of the so-called Twin Systems approach).
read more
About: This article is published in Artificial Intelligence. The article was published on 01 May 2021. and is currently open access.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review
Anna Markella Antoniadi,Yuhan Du,Yasmine Guendouz,Lan Wei,Claudia Mazo,Brett A. Becker,Catherine Mooney +6 more
TL;DR: An overall distinct lack of application of XAI is found in the context of CDSS and, in particular, a lack of user studies exploring the needs of clinicians is found.
373
Explainable artificial intelligence: a comprehensive review
TL;DR: A review of explainable artificial intelligence (XAI) can be found in this article, where the authors analyze and review various XAI methods, which are grouped into (i) pre-modeling explainability, (ii) interpretable model, and (iii) post-model explainability.
363
•Posted Content
On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning
Eoin M. Kenny,Mark T. Keane +1 more
TL;DR: The present method, called PlausIble Exceptionality-based Contrastive Explanations (PIECE), modifies all exceptional features in a test image to be normal from the perspective of the counterfactual class, showing that PIECE not only generates the most plausiblecounterfactuals on several measures, but also the best semifactuals.
114
Transparency of AI in Healthcare as a Multilayered System of Accountabilities: Between Legal Requirements and Technical Limitations
TL;DR: This paper suggests an interdisciplinary vision on how to tackle the issue of AI's transparency in healthcare, and proposes a single point of reference for both legal scholars and data scientists on transparency and related concepts.
How transparency modulates trust in artificial intelligence
TL;DR: In this article , the authors present opposition (extreme algorithm aversion or distrust) and loafing (extreme automation complacency or bias) as lying at opposite ends of a spectrum, with algorithmic vigilance representing an ideal mid-point.
98
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
51.9K
•Proceedings Article
A unified approach to interpreting model predictions
Scott M. Lundberg,Su-In Lee +1 more
- 04 Dec 2017
TL;DR: In this article, a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), is presented, which assigns each feature an importance value for a particular prediction.
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Marco Tulio Ribeiro,Sameer Singh,Carlos Guestrin +2 more
- 13 Aug 2016
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.