5 papers
Explaining Motion Relevance for Activity Recognition in Video Deep Learning Models
Liam Hiley, Alun Preece, Yulia Hicks +3
A small subset of explainability techniques developed initially for image recognition models has recently been applied for interpretability of 3D Convolutional Neural Network model…
Sanity Checks for Saliency Metrics
Richard Tomsett, Dan Harborne, Supriyo Chakraborty +2
Saliency maps are a popular approach to creating post-hoc explanations of image classifier outputs. These methods produce estimates of the relevance of each pixel to the classifica…
Illuminated Decision Trees with Lucid
David Mott, Richard Tomsett
The Lucid methods described by Olah et al. (2018) provide a way to inspect the inner workings of neural networks trained on image classification tasks using feature visualization.…
Stakeholders in Explainable AI
Alun Preece, Dan Harborne, Dave Braines +2
There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable. However, there is no general c…
Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems
Richard Tomsett, Dave Braines, Dan Harborne +2
Several researchers have argued that a machine learning system's interpretability should be defined in relation to a specific agent or task: we should not ask if the system is inte…