The show you’re about to hear is part of a series of shows recorded in San Francisco at the Artificial Intelligence Conference. This time around, I speak with Mo Patel, practice director of AI & deep learning and Laura Frølich, data scientist, of Think Big Analytics. Mo and Laura joined me at the AI conference after their session on “Training vision models with public transportation datasets.”
Subscribe: iTunes / Google Play / Spotify / RSS
We talked over a bunch of use cases they’ve worked on involving image analysis and deep learning, including an assisted driving system. We also talk through a bunch of practical challenges faced when working on real machine learning problems, like feature detection, data augmentation, and training data.
TWIML Online Meetup
The details for the upcoming TWIML Online Meetup have been set!! On Oct 18 at 3pm PT, We will discuss the paper Visual Attribute Transfer through Deep Image Analogy, by Jing Liao and others from Microsoft Research. The discussion will be led by Duncan Stothers. (Thanks Duncan!) For anyone who’s has missed the last two meetups, or for those that haven’t yet joined the group, please visit twimlai.com/meetup. There you’ll find Video Recaps of the last 2 meetups, along with a link to the paper we’ll be reviewing next month. If you’d like to present your favorite paper, we’d love to have you do it. Just shoot us an email at firstname.lastname@example.org to get the ball rolling.
Thanks to our Sponsor
A big thank you to Intel Nervana for their continued support of the podcast! At the AI Conference, Intel Nervana announced the DevCloud, a cloud-hosted hardware and software platform for learning, sandboxing and accelerating the development of AI solutions. The Intel Nervana DevCloud will be available to 200,000 developers, researchers, academics and startups via the Intel Nervana AI Academy this month. For more information on the DevCloud or the AI Academy, visit intelnervana.com/devcloud. Be sure to let them know via Twitter @IntelNervana how much you appreciate their support of the podcast.