Interactive slice visualization for exploring machine learning models
This addresses the problem of model interpretability for users of machine learning, though it is incremental as it builds on existing visualization techniques.
The paper tackles the interpretability deficit of machine learning models by using interactive visualization of slices of predictor space to open up the black-box, enabling interrogation, explanation, validation, and comparison of model fits, implemented in the R package condvis2.
Machine learning models fit complex algorithms to arbitrarily large datasets. These algorithms are well-known to be high on performance and low on interpretability. We use interactive visualization of slices of predictor space to address the interpretability deficit; in effect opening up the black-box of machine learning algorithms, for the purpose of interrogating, explaining, validating and comparing model fits. Slices are specified directly through interaction, or using various touring algorithms designed to visit high-occupancy sections or regions where the model fits have interesting properties. The methods presented here are implemented in the R package \pkg{condvis2}.