Deep Learning for Population Genetic Inference with Dan Schrider

800 800 The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Today we’re joined by Dan Schrider, assistant professor in the department of genetics at The University of North Carolina at Chapel Hill.

My discussion with Dan starts with an overview of population genomics and from there digs into his application of machine learning in the field, allowing us to, for example, better understand population size changes and gene flow from DNA sequences. We then dig into Dan’s paper “The Unreasonable Effectiveness of Convolutional Neural Networks in Population Genetic Inference,” which was published in the Molecular Biology and Evolution journal, which examines the idea that CNNs are capable of outperforming expert-derived statistical methods for some key problems in the field.

Join me at Pegaworld!

We’d like to join Pegasystems, who is sponsoring today’s episode, in inviting you to meet meat the MGM Grand in Las Vegas June 2nd-5th at PegaWorld, the company’s annual digital transformation conference.

Pegasystems puts AI at the center of its customer engagement software so that it optimizes every customer touchpoint on every channel in real time. That way each interaction is relevant and timely to each individual customer, no matter if it’s a sales call, a digital marketing campaign or a customer service chat either online or in-store, and the system always learning in real-time to make the next interaction better.

Pegas customers are the real stars at PegaWorld. There you’ll hear great stories of AI applied to the customer experience at real Pega customers. The event is a great way to learn from a who’s who of the Fortune 500, and of course, I’ll be there and speaking as well.

To register, visit and use the promo code TWIML19 when you sign up for $200 off. Again that’s TWIML19. It’s as easy at that. Hope to see you there!

About Dan

Mentioned in the Interview

“More On That Later” by Lee Rosevere licensed under CC By 4.0

Leave a Reply

Your email address will not be published.