← Search

Kieran Campbell

2 accepted papers

2020

What went wrong and when? Instance-wise feature importance for time-series black-box models

NeurIPS 2020poster

Explanations of time series models are useful for high stakes applications like healthcare but have received little attention in machine learning literature. We propose FIT, a framework that evaluates the importance of observations for a multivariate time-series black-box model by quantifying the sh…

2019

Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models

ICML 2019oral

The interpretation of complex high-dimensional data typically requires the use of dimensionality reduction techniques to extract explanatory low-dimensional representations. However, in many real-world problems these representations may not be sufficient to aid interpretation on their own, and it wo…