This Week in Machine Learning & AI This Week in Machine Learning & AI This Week in Machine Learning & AI This Week in Machine Learning & AI This Week in Machine Learning & AI

    LSTM’s, plus a Deep Learning History Lesson with Jürgen Schmidhuber

    800 800 This Week in Machine Learning & AI

    This week we have a very special interview to share with you! Those of you who’ve been receiving my newsletter for a while might remember that while in Switzerland last month, I had the pleasure of interviewing Jürgen Schmidhuber, in his lab at IDSIA, which is the Dalle Molle Institute for Artificial Intelligence Research in Lugano, Switzerland, where he serves as Scientific Director.

    In addition to his role at IDSIA, Jürgen is also Co-Founder and Chief Scientist of NNaisense, a company that is using AI to build large-scale neural network solutions for “superhuman perception and intelligent automation.”

    Jürgen is an interesting, accomplished and in some circles controversial figure in the AI community and we covered a lot of very interesting ground in our discussion, so much so that I couldn’t truly unpack it all until I had a chance to sit with it after the fact. We talked a bunch about his work on neural networks, especially LSTM’s, or Long Short-Term Memory networks, which are a key innovation behind many of the advances we’ve seen in deep learning and its application over the past few years. Along the way, Jürgen walks us through a deep learning history lesson that spans 50+ years. It was like walking back in time with the Three-Eyed Raven. I know you’re really going to enjoy this one, and by the way, this is definitely a nerd alert show!

    TWiML Online Meetup

    Don’t forget to register for our online meetup! If you missed the first meetup, we expect to have the recording up by the end of the day, 8/28. You’ll be able to view it at twimlai.com/meetup, which is also where you can register for the next one, which will be held on Tuesday, September 12, at 3pm Pacific Time. We’re currently finalizing the topic, but if you’re registered we’ll notify you as soon as that’s done.

    Thanks to Our Sponsors

    Thank you to our friends at Cloudera for sponsoring this episode. Yes, they are the Hadoop company, but did you know they also offer software for data science and deep learning? The idea is pretty simple: If you work for a large enterprise you probably already have Hadoop in place, and your Hadoop cluster is filled with lots of data that you want to use in building your models. But you still need to easily access that data, process it using the latest open source tools and harness bursts of compute power to train your models. This is where Cloudera’s Data Science Workbench comes in. With Data Science Workbench, Cloudera can help you get up and running with deep learning without massive new investments, by implementing an on-demand self-service deep learning platform on existing CDH clusters.

    The folks at Cloudera are so confident that you’re going to like what you see, that for a limited time, they’re offering a drone to qualified participants, simply for meeting with their sales representative for a demonstration of Cloudera’s Data Science Workbench.

    For your demo and drone, visit twimlai.com/cloudera

    The Artificial Intelligence Conference

    I’ll be in SF September 18-20 for the Artificial Intelligence Conference, and hope to see you there too! If you’ve already registered, send me a shout on twitter and let me know! If you are still interested in coming, but haven’t registered just yet, use code PCTWIML, it’s good for 20% off of most conference packages!

    About Jürgen

    Mentioned in the Interview

    1 comment
    • Thomas Young Olesen
      REPLY

      Thanks for another great talk! I enjoy all the casts during commute and they are a great source of inspiration.

      I also wanted to share my favorite quote from this episode. I think this quote was appropriately understated to be really funny and interesting in the same time.

      “…if you look at the LSTM it’s just five lines of pseudo code. So it’s very simple. It’s not the full true A.I. thing yet, because there you have to have the full loop through the environment: act, perceive, act, perceive, act, perceive, maximize future reward or reward until the end of your lifetime. And for that i sometimes speculate we need another five lines…” [@55m50s]

    Leave a Reply

    Your email address will not be published.