Robotic Perception and Control with Chelsea Finn

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

Our third guest in the Industrial AI series is Chelsea Finn,  PhD student at UC Berkeley. Despite being early in her career, Chelsea is an accomplished researcher with more than 14 published papers in the past 2 years, on subjects like Deep Visual Foresight , Model-Agnostic Meta-Learning and Visuomotor Learning to name a few. We discuss all of these topics in the show, as well as subjects like zero-shot, one-shot and few-shot learning.

Chelsea also gives some advice to all PhD students out there just like herself. We spend some time at the end of the interview talking about this, and she has some great words of wisdom for current and prospective PhD students but also independent learners in the field.  

Nerd Alert!!

Chelsea and I really dig deep into these learning methods and techniques, and this conversation gets pretty technical at times, to the point that I had a tough time keeping up myself, so hang in there. I promise that you’ll learn a ton if you keep with it.

About the Industrial AI Series

This show is part of our Industrial AI series. I’ve mentioned my interest in industrial applications of machine learning & AI a few times on the podcast. I’ve been doing some research in the area, and I’m very close to publishing a special report on the topic. If you’re interested in learning more about this project, the report, or the podcast series as a whole, check out our Industrial AI page.

Thanks to Our Sponsor

Bonsai LogoA big thank you to Bonsai, who is supporting my work in this area. I’ve been following them since their launch just over a year ago, and I’ve been impressed with their team and technology. If you’re building AI-powered applications to optimize and control enterprise systems, check them out at Please let them know you appreciate their support of the podcast.


Next week I’m at the O’Reilly AI conference in New York City. You can still register using our discount code PCTWIML for 20% off. If you live in New York or will be at the event, let’s plan to meet up! I’m partnering with the NY AI meetup to host a happy hour on Thursday evening after the event. If you’d like more details please sign up using the form at

About Chelsea

Mentioned in the Interview

  • Jason

    Fantastic episode; really enjoyed the technical details! Looking forward to reading Chelsea’s work. I’m also very interested in your idea of a virtual reading group so lmk if that comes to fruition.

  • Joseph Anthony Perez

    I find this episode, like many of your previous ones, fantastic. I learn tremendous amounts by following your podcasts and looking up some of the mentioned topics and sources. I would be very happy to participate in a virtual reading group, if you were to initiate this concept. I am also recommending your site and podcasts to many of my interested colleagues via our corporate website (intranet).

    Your faithful follower and listener,

    Joe (in Germany)

  • Michael Allen

    Great podcast – again!!!!

    I too would be interested in a virtual reading group. I’m a biomedical and healthcare scientist looking at use of ML in healthcare decisions (first as an audit of decisions previously made). I am stronger on the medical side than the coding use (largely I use SciKit learn though I have played with coding some NN ‘from scratch’). Am I’m stronger at coding than pure math. So I’d appreciate help from others linking any math to code.

    TWIML has been really useful for me.


  • Thomas Paula

    Great episode, again! It was great to go deeper in the technical stuff and understand more about details and the challenges in Robotics.

    I’m really interested in this reading group and I’d be very happy to participate.


  • Abdurrahman Ahmed

    Great episode, even though the technical bits were the hardest for me to follow thus far!

    I am also very interested in joining a ML reading group. I find it demotivating to try to cope with this very fast moving field on my own! I think the reading group will offer a more motivating and helpful atmosphere for keeping up with the main ideas and trends in the field.

  • Marc Meketon

    I too find your podcasts informative and useful.

    Chelsea was amazing… wish I could better understand more of the technology that is involved in her work.

    I would also enjoy being involved in a discussion group focused on important papers. As long as we don’t go too fast (maybe a paper a month).

  • Brian B

    Excellent episode.

    Let’s do that virtual reading group. Maybe start with a list of papers someone working in ML/AI should already be familiar with?

  • Andrew Schell

    Hello Twiml!

    I am a Sata Science undergrad in Seattle and would be happy to lead a study reading group a night each month or perhaps twice per month.

    I have a corpus of dozens of books on my ‘to read’ list and would be happy to work with others to collect or pick books.

Leave a Reply

Your email address will not be published.