Picture for Lisa Schut

Lisa Schut

DeDUCE: Generating Counterfactual Explanations Efficiently

Nov 29, 2021
Benedikt Höltgen, Lisa Schut, Jan M. Brauner, Yarin Gal

Figure 1 for DeDUCE: Generating Counterfactual Explanations Efficiently

Figure 2 for DeDUCE: Generating Counterfactual Explanations Efficiently

Figure 3 for DeDUCE: Generating Counterfactual Explanations Efficiently

Figure 4 for DeDUCE: Generating Counterfactual Explanations Efficiently

* Presented at the 1st Workshop on eXplainable AI approaches for debugging and diagnosis ([email protected])

Access Paper or Ask Questions

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Mar 16, 2021
Lisa Schut, Oscar Key, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal

Figure 1 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Figure 2 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Figure 3 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Figure 4 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

* Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021
* 21 pages, 13 Figures

Access Paper or Ask Questions

A Bayesian Perspective on Training Speed and Model Selection

Oct 27, 2020
Clare Lyle, Lisa Schut, Binxin Ru, Yarin Gal, Mark van der Wilk

Figure 1 for A Bayesian Perspective on Training Speed and Model Selection

Figure 2 for A Bayesian Perspective on Training Speed and Model Selection

Figure 3 for A Bayesian Perspective on Training Speed and Model Selection

Figure 4 for A Bayesian Perspective on Training Speed and Model Selection

* To be presented at NeurIPS 2020

Access Paper or Ask Questions

Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search

Jun 08, 2020
Binxin Ru, Clare Lyle, Lisa Schut, Mark van der Wilk, Yarin Gal

Figure 1 for Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search

Figure 2 for Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search

Figure 3 for Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search

Figure 4 for Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search

* 14 pages, 10 figures

Access Paper or Ask Questions