Neural Networks, Differential Equations, and Neural ODEs

WE'RE BACK—welcome to the DC/NoVA Papers We Love meetup!

Papers We Love is an international organization centered around the appreciation of computer science research papers. There's so much we can learn from the landmark research that shaped the field and the current studies that are shaping our future. Our goal is to create a community of tech professionals passionate about learning and sharing knowledge. Come join us!

New to research papers? Watch The Refreshingly Rewarding Realm of Research Papers (https://www.youtube.com/watch?v=8eRx5Wo3xYA) by Sean Cribbs.

// Tentative Schedule

• 7:00-7:15–Introduction and Announcements

• 7:15-8:40–Neural Networks, Differential Equations, and Neural ODEs, led by Lee Sharma

• 8:40-9:00–Informal paper discussion

// Papers

The talk will do a deep-dive of the Neural ODE paper (https://arxiv.org/pdf/1806.07366.pdf) and some of its descendants. Through slides, demonstration, and discussion, we'll discuss the context, methodology, and implementation of Neural Ordinary Differential Equations and, more broadly, explore the exciting research area at the intersection of differential equations and neural networks.

I recommend the repository at awesome-neural-ode: https://github.com/Zymrael/awesome-neural-ode It goes beyond the basic algorithm and discusses other issues in implicit-layered networks and the growing intersection of dynamical systems, differential equations, and neural networks.