Search

Rapid improvements in the performance of machine learning models have pushed them to the forefront of data-driven decision-making. Meanwhile, the increased integration of these models into various application domains has further highlighted the need for greater interpretability and transparency. To identify problems such as bias, overfitting, and incorrect correlations, data scientists require tools that explain the mechanisms with which these model decisions are made. In this paper we introduce AdViCE, a visual analytics tool that aims to guide users in black-box model debugging and validation. The solution rests on two main visual user interface innovations: (1) an interactive visualization design that enables the comparison of decisions on user-defined data subsets; (2) an algorithm and visual design to compute and visualize counterfactual explanations - explanations that depict model outcomes when data features are perturbed from their original values. We provide a demonstration of the tool through a use case that showcases the capabilities and potential limitations of the proposed approach., Comment: 4 pages, 2 figures, IEEE VIS 2021 Machine learning, interpretability, explainability, counterfactual explanations, data visualization

The continued improvements in the predictive accuracy of machine learning models have allowed for their widespread practical application. Yet, many decisions made with seemingly accurate models still require verification by domain experts. In addition, end-users of a model also want to understand the reasons behind specific decisions. Thus, the need for interpretability is increasingly paramount. In this paper we present an interactive visual analytics tool, ViCE, that generates counterfactual explanations to contextualize and evaluate model decisions. Each sample is assessed to identify the minimal set of changes needed to flip the model's output. These explanations aim to provide end-users with personalized actionable insights with which to understand, and possibly contest or improve, automated decisions. The results are effectively displayed in a visual interface where counterfactual explanations are highlighted and interactive methods are provided for users to explore the data and model. The functionality of the tool is demonstrated by its application to a home equity line of credit dataset., Comment: 4 pages, 2 figures, ACM IUI 2020

In this paper we revisit the problem of a nematic liquid crystal in contact with patterned substrates. The substrate is modelled as a periodic array of parallel infinite grooves of well-defined cross section sculpted on a chemically homogeneous substrate which favors local homeotropic anchoring of the nematic. We consider three cases: a sawtooth, a crenellated and a sinusoidal substrate. We analyse this problem within the modified Frank-Oseen formalism. We argue that, for substrate periodicities much larger than the extrapolation length, the existence of different nematic textures with distinct far-field orientations, as well as the anchoring transitions between them, are associated with the presence of topological defects either on or close to the substrate. For the sawtooth and sinusoidal case, we observe a homeotropic to planar anchoring transition as the substrate roughness is increased. On the other hand, a homeotropic to oblique anchoring transition is observed for crenellated substrates. In this case, the anchoring phase diagram shows a complex dependence on the substrate roughness and substrate anchoring strength., Comment: 36 pages, 15 figures, revised version submitted to Journal of Physics: Condensed Matter