We present Learning to Explain (LTX), a model-agnostic framework designed for providing post-hoc explanations for vision models. The LTX framework introduces an “explainer” …
The quest for transparency in black-box models has gained significant momentum in recent years. In particular, discovering the underlying machine learning technique type (or model …
Deep Learning models provide state of the art classification results, but are not human- interpretable. We propose a novel method to interpret the classification results of a black box …
X Renard, N Woloszko, J Aigrain… - arXiv preprint arXiv …, 2019 - arxiv.org
Interpretable surrogates of black-box predictors trained on high-dimensional tabular datasets can struggle to generate comprehensible explanations in the presence of …
P Rasouli, IC Yu - 2021 International Joint Conference on …, 2021 - ieeexplore.ieee.org
The research around developing methods for debugging and refining Machine Learning (ML) models is still in its infancy. We believe employing tailored tools in the development …
P Rasouli, IC Yu - 2020 International joint conference on neural …, 2020 - ieeexplore.ieee.org
Defining a representative locality is an urgent challenge in perturbation-based explanation methods, which influences the fidelity and soundness of explanations. We address this issue …
As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain …
A Gosiewska, A Gacek, P Lubon, P Biecek - arXiv preprint arXiv …, 2019 - arxiv.org
Complex black-box predictive models may have high accuracy, but opacity causes problems like lack of trust, lack of stability, sensitivity to concept drift. On the other hand, interpretable …
In recent years, understanding the decision-making process of black-box models has become not only a legal requirement but also an additional way to assess their performance …