In this paper, we present DendroMap, a novel approach to interactively exploring large-scale image datasets for machine learning (ML). ML practitioners often explore image datasets by generating a grid of images or projecting high-dimensional representations of images into 2-D using dimensionality reduction techniques (e.g., t-SNE). However, neither approach effectively scales to large datasets because images are ineffectively organized and interactions are insufficiently supported. To address these challenges, we develop DendroMap by adapting Treemaps, a well-known visualization technique. DendroMap effectively organizes images by extracting hierarchical cluster structures from high-dimensional representations of images. It enables users to make sense of the overall distributions of datasets and interactively zoom into specific areas of interests at multiple levels of abstraction. Our case studies with widely-used image datasets for deep learning demonstrate that users can discover insights about datasets and trained models by examining the diversity of images, identifying underperforming subgroups, and analyzing classification errors. We conducted a user study that evaluates the effectiveness of DendroMap in grouping and searching tasks by comparing it with a gridified version of t-SNE and found that participants preferred DendroMap. DendroMap is available at https://div-lab.github.io/dendromap/.

Intergenerational making activities provide an opportunity for family collaboration where parents and children learn together. We discuss the facilitative moves that emerged between researchers, parents, and children during a half-day making program where participants played and created games. Four families with a variety of knowledge of digital fabrication technologies participated in three activities: playing a variety of games, designing and making their own games using arts and crafts materials, and optionally utilizing digital fabrication tools to complete their games. We position traditional fabrication and digital fabrication as two different modalities of making. Accordingly, we examine the facilitative moves and behavioral shifts that emerge across the two modalities and as observed through qualitative analysis. This work contributes insights to the field on program structure and the ways formal facilitators and parents can sustain child engagement in a making workshop.