Machine Learning Lunch Meeting

Everyone is invited to the weekly machine learning lunch meetings, where our faculty members from Computer Science, Statistics, ECE, and other departments will discuss their latest groundbreaking research in machine learning. This is an opportunity to network with faculty and fellow researchers and to learn about the cutting-edge research being conducted at our university.

Speaker: Kris Sankaran

Abstract: The main theme of this talk is that visualization plays a central, if largely unsung, role in the design and application of deep learning models. Indeed, in addition to guiding practical model training and evaluation, they can help improve mental models about system components. We will explore variations on this theme, seeing how visualization principles can inform deep learning practice and highlighting how visualization has shaped the community’s understanding of memory and attention mechanisms. We will visit both serious (https://go.wisc.edu/d3s65o, https://go.wisc.edu/m9llck) and fanciful (https://go.wisc.edu/lk38zd) visualizations from my past projects, with the goal that you might leave with at least one visualization idea relevant to your work. Finally, I will offer early thoughts on how visualization of model-derived representations can inform scientific discussion, especially in the genomics literature.