Thinking about grad school next year? Interested in visualization, human/AI interaction, computational art?
Consider Harvard! @wattenberg and I are building up our lab and will be looking for students.
Our DMs are open.
Fernanda Viégas
286 posts
Fernanda Viégas
@viegasf
Human/AI Interaction and data visualization. Professor at Harvard. Co-founder of Google's People+AI Research initiative (PAIR)
Joined February 2009
- Our group open sourced Facets: tools to debug your data before debugging your machine learning model research.googleblog.com/2017/07/facets…
GIF - Visualize transformer attention! ✨ AttentionViz, created by Catherine Yeh and expanded by Yida Chen, helps you explore transformer self-attention by visualizing query and key vectors in a joint embedding. Paper: arxiv.org/abs/2305.03210 Website: attentionviz.com
- So excited to announce deeplearn.js: an open source WebGL-accelerated JS library for ML that runs in your browser research.googleblog.com/2017/08/harnes…
GIF - I’m thrilled to announce that, as of January 2022, I’ll be joining Harvard as a professor of computer science, with an affiliation with the business school. @wattenberg joins in fall 2021! We’ll also continue to work, part-time, at Google and on PAIR. seas.harvard.edu/news/2020/11/t…
- Yesterday @wattenberg and I gave a tutorial at #NeurIPS2018 on Data Visualization for Machine Learning. Here it is: facebook.com/nipsfoundation…
- Working on visualizations for AI explainability? Consider submitting to our workshop, part of the IEEE VIS conference: visxai.io
- Check out PAIR's What-If Tool: Code-Free Probing of Machine Learning Models. It allows you to test for multiple ML Fairness measures: ai.googleblog.com/2018/09/the-wh…
GIF - Attacking discrimination with smarter machine learning, work with @wattenberg and @mrtz; see the tradeoffs here research.google.com/bigpicture/att…
GIF - Psyched to announce a new collection of essays on PAIR's human-centered approach to designing with ML and AI: design.google/library/ai/
- Want to visualize high-dimensional data? Try out the brand new Embedding Projector: projector.tensorflow.org
GIF - t-SNE multi-dimensional plots can sometimes mislead, see how to use them effectively: distill.pub/2016/misread-t… with @wattenberg & @enjalot
- Unreasonably excited about having an updated website: fernandaviegas.com Huge thank you to my awesome husband @danmartines!
