Picture for Benjamin Rothwell

Benjamin Rothwell

EFI: A Toolbox for Feature Importance Fusion and Interpretation in Python

Add code
Aug 08, 2022
Figure 1 for EFI: A Toolbox for Feature Importance Fusion and Interpretation in Python
Figure 2 for EFI: A Toolbox for Feature Importance Fusion and Interpretation in Python
Figure 3 for EFI: A Toolbox for Feature Importance Fusion and Interpretation in Python
Figure 4 for EFI: A Toolbox for Feature Importance Fusion and Interpretation in Python
Viaarxiv icon

Anomaly Detection for Unmanned Aerial Vehicle Sensor Data Using a Stacked Recurrent Autoencoder Method with Dynamic Thresholding

Add code
Mar 09, 2022
Figure 1 for Anomaly Detection for Unmanned Aerial Vehicle Sensor Data Using a Stacked Recurrent Autoencoder Method with Dynamic Thresholding
Figure 2 for Anomaly Detection for Unmanned Aerial Vehicle Sensor Data Using a Stacked Recurrent Autoencoder Method with Dynamic Thresholding
Figure 3 for Anomaly Detection for Unmanned Aerial Vehicle Sensor Data Using a Stacked Recurrent Autoencoder Method with Dynamic Thresholding
Figure 4 for Anomaly Detection for Unmanned Aerial Vehicle Sensor Data Using a Stacked Recurrent Autoencoder Method with Dynamic Thresholding
Viaarxiv icon

Mechanistic Interpretation of Machine Learning Inference: A Fuzzy Feature Importance Fusion Approach

Add code
Oct 22, 2021
Figure 1 for Mechanistic Interpretation of Machine Learning Inference: A Fuzzy Feature Importance Fusion Approach
Figure 2 for Mechanistic Interpretation of Machine Learning Inference: A Fuzzy Feature Importance Fusion Approach
Figure 3 for Mechanistic Interpretation of Machine Learning Inference: A Fuzzy Feature Importance Fusion Approach
Figure 4 for Mechanistic Interpretation of Machine Learning Inference: A Fuzzy Feature Importance Fusion Approach
Viaarxiv icon

Towards a More Reliable Interpretation of Machine Learning Outputs for Safety-Critical Systems using Feature Importance Fusion

Add code
Sep 11, 2020
Figure 1 for Towards a More Reliable Interpretation of Machine Learning Outputs for Safety-Critical Systems using Feature Importance Fusion
Figure 2 for Towards a More Reliable Interpretation of Machine Learning Outputs for Safety-Critical Systems using Feature Importance Fusion
Figure 3 for Towards a More Reliable Interpretation of Machine Learning Outputs for Safety-Critical Systems using Feature Importance Fusion
Figure 4 for Towards a More Reliable Interpretation of Machine Learning Outputs for Safety-Critical Systems using Feature Importance Fusion
Viaarxiv icon