Fighting Fake News and Deep Fakes with Machine Learning w/ Delip Rao - TWiML Talk #260


Manage episode 232642178 series 2355587
By Discovered by Player FM and our community — copyright is owned by the publisher, not Player FM, and audio streamed directly from their servers.

Today we’re joined by Delip Rao, vice president of research at the AI Foundation, co-author of the book Natural Language Processing with PyTorch, and creator of the Fake News Challenge.

Our conversation begins with the origin story of the Fake News Challenge, including Delip’s initial motivations for the project, and what some of his key takeaways were from that experience. We then dive into a discussion about the generation and detection of artificial content, including “fake news” and “deep fakes.” We discuss the state of generation and detection for text, video, and audio, the key challenges in each of these modalities, the role of GANs on both sides of the equation, and other potential solutions. Finally, we discuss Delip’s new book, Natural Language Processing with PyTorch and his philosophy behind writing it.

The complete show notes for this episode can be found at

For more from the AI Conference NY series, visit

Thanks to our friends at HPE for sponsoring this week's series of shows from the O’Reilly AI Conference in New York City! For more information on HPE InfoSight, visit

289 episodes available. A new episode about every 2 days averaging 46 mins duration .