Visualization can play a critical role in helping humans work with machine intelligence. We'll show a series of examples of the power of visualization in various domains, and discuss how it helps researchers understand the inner workings of deep networks, how engineers can use it to debug complex systems, and how students can use it to learn about machine learning itself. Throughout, we will describe the design process we follow in creating these visualizations.

Bios: Fernanda Viégas, Martin Wattenberg, and Daniel Smilkov are researchers in Google Brain. They are well known for their contributions to social and collaborative visualization, and the systems they’ve created are used daily by millions of people. Viégas holds a Ph.D. from the MIT Media Lab; Wattenberg has a Ph.D. in mathematics from U.C. Berkeley; Smilkov has an M.S. from the MIT Media Lab. All three have created visualization-based artwork, which has been exhibited worldwide.