RNNbow: Visualizing Learning via Backpropagation Gradients in Recurrent Neural Networks

no code implementations • 29 Jul 2019 • Dylan Cashman, Genevieve Patterson, Abigail Mosca, Nathan Watts, Shannon Robinson, Remco Chang

RNNbow is a web application that displays the relative gradient contributions from Recurrent Neural Network (RNN) cells in a neighborhood of an element of a sequence.

A User-based Visual Analytics Workflow for Exploratory Model Analysis

no code implementations • 27 Sep 2018 • Dylan Cashman, Shah Rukh Humayoun, Florian Heimerl, Kendall Park, Subhajit Das, John Thompson, Bahador Saket, Abigail Mosca, John Stasko, Alex Endert, Michael Gleicher, Remco Chang

We found that our system workflow enabled users to generate complex models, to assess them for various qualities, and to select the most relevant model for their task.

AutoML Model Selection