Implicit Self-Regularization in Deep Neural Networks

Implicit Self-Regularization in Deep Neural Networks

This video is a recap of our February 2019 Americas TWIML Online Meetup.

In this month’s community segment, we discuss the first TWIML Live – The OpenAI Panel discussion, the last Americas meetup, and the OpenAI’s GPT-2 language model.

In our presentation segment, Charles Martin, PhD, leads a discussion on “Implicit Self-Regularization in Deep Neural Networks” with the paper on “Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning” by himself and Michael W. Mahoney.

For links to the papers, podcasts, and more mentioned above or during this meetup, for more information on previous meetups, or to get registered for upcoming meetups, visit twimlai.com/meetup!

 

Paper mentioned in the presentation:

Mentioned in the community segment:

Topic: Implicit Self-Regularization in Deep Neural Networks
Presenter: Charles Martin, PhD
Date: Wednesday 20th February 2019
Time: 17:00 PM US Pacific Time