267 citations · 958 across the 28 of their papers we have counts for
4 papers · 1 filter
UnProjection: Leveraging Inverse-Projections for Visual Analytics of High-Dimensional Data
Mateus Espadoto, Gabriel Appleby, Ashley Suh +6
Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Altho…
Comparing Deep Neural Nets with UMAP Tour
Mingwei Li, Carlos Scheidegger
Neural networks should be interpretable to humans. In particular, there is a growing interest in concepts learned in a layer and similarity between layers. In this work, a tool, UM…
STFT-LDA: An Algorithm to Facilitate the Visual Analysis of Building Seismic Responses
Zhenge Zhao, Danilo Motta, Matthew Berger +5
Civil engineers use numerical simulations of a building's responses to seismic forces to understand the nature of building failures, the limitations of building codes, and how to d…
Human-in-the-loop Extraction of Interpretable Concepts in Deep Learning Models
Zhenge Zhao, Panpan Xu, Carlos Scheidegger +1
The interpretation of deep neural networks (DNNs) has become a key topic as more and more people apply them to solve various problems and making critical decisions. Concept-based e…