Interpretable by Design: Wrapper Boxes Combine Neural Performance with Faithful Explanations
Can we preserve the accuracy of neural models while also providing faithful explanations?
We present wrapper boxes, a general approach to generate faithful, example-based …
We present wrapper boxes, a general approach to generate faithful, example-based …
Wrapper Boxes for Faithful Attribution of Model Predictions to Training Data
Can we preserve the accuracy of neural models while also providing faithful explanations of
model decisions to training data? We propose a “wrapper box” pipeline: training a neural …
model decisions to training data? We propose a “wrapper box” pipeline: training a neural …
Explore, Support, and Interact: Scaling Interpretable and Explainable Machine Learning up to Realities of Biomedical Data
R Marcinkevičs - 2024 - research-collection.ethz.ch
Performant machine learning models are becoming increasingly complex and large. Due to
their black-box design, they often have limited utility in exploratory data analysis and evoke …
their black-box design, they often have limited utility in exploratory data analysis and evoke …
Explanations and Processes to Enable Humans to Assess AI with Respect to Manipulable Properties
JE Dodge - 2022 - ir.library.oregonstate.edu
Assessing AI systems is difficult. Humans rely on AI systems in increasing ways, both visible
and invisible, meaning a variety of stakeholders need a variety of assessment tools (eg, a …
and invisible, meaning a variety of stakeholders need a variety of assessment tools (eg, a …
[PDF][PDF] Case-based Explanation: Making the Implicit Explicit.
D Leake - ICCBR Workshops, 2022 - ceur-ws.org
Case-based explanation (CBE) is seen by many as a compelling method for explaining
black-box systems, and is advocated and pursued in substantial research in the CBR …
black-box systems, and is advocated and pursued in substantial research in the CBR …