Explainable bayesian optimization
T Chakraborty, C Seifert, C Wirth - ar** guidelines for functionally-grounded evaluation of explainable artificial intelligence using tabular data
Abstract Explainable Artificial Intelligence (XAI) techniques are used to provide transparency
to complex, opaque predictive models. However, these techniques are often designed for …
to complex, opaque predictive models. However, these techniques are often designed for …
Post-hoc rule based explanations for black box bayesian optimization
Abstract Explainable Artificial Intelligence (XAI) aims to enhance transparency and trust in AI
systems by providing insights into their decision-making processes. While there has been …
systems by providing insights into their decision-making processes. While there has been …
MMD-based Variable Importance for Distributional Random Forest
Abstract Distributional Random Forest (DRF) is a flexible forest-based method to estimate
the full conditional distribution of a multivariate output of interest given input variables. In this …
the full conditional distribution of a multivariate output of interest given input variables. In this …
A sea of words: an in-depth analysis of anchors for text data
G Lopardo, F Precioso, D Garreau - ar** tools capable of explaining their predictions and quantifying the associated …
Understanding Post-hoc Explainers: The Case of Anchors
In many scenarios, the interpretability of machine learning models is a highly required but
difficult task. To explain the individual predictions of such models, local model-agnostic …
difficult task. To explain the individual predictions of such models, local model-agnostic …