Join Boulder Geo Meetup for NVIDIA Deep Learning Institute Presents Deep Learning From Space: Episode 2!
Join us to learn about how deep learning is being applied to better understand the world from Space!With the recent explosion in commercial medium to high resolution satellite providers combined with advances in GPU hardware and large corpuses of labeled data, researchers are turning to machines to help them understand our planet. This month’s meetup will be sponsored by the
. We’ll be changing up the format slightly this time to give everyone an opportunity to get their hands dirty applying deep learning to some real-world remote sensing data.
Jon Barker from NVIDIA (6:30-7:00) will talk about different approaches to object detection in remote sensing imagery using deep learning. There are a variety of ways to train and deploy a deep neural network for object detection in remote sensing imagery. The choice of method depends on the type of training data you have and the requirements for speed and accuracy in the deployed model. This talk with cover the pros and cons of the different approaches.
Lab: (7:00-8:30) We will run a hands-on lab giving you the opportunity to train different types of object detector and evaluate their performance on some real-world remote sensing data. The lab will run from the cloud with each person working through the material on their own GPU-enabled server. Some of NVIDIA’s deep learning experts will be on hand to answer any questions as we go through. All you need to bring to take part is a laptop with a modern web browser.
Networking: 8:30-9:00 As always this event is open to individuals from all backgrounds, whether you’re just starting out in Geo, interested in Data Science, or are a full blown Machine Learning… machine! We have to work within the maximum capacity of the venue, so it is essential that you sign-up for the meetup if you intend to come and names will be checked on the door. If you haven’t signed up here you will unfortunately be turned away. There will also be a waitlist if needed, so please ensure you free up your space if you can’t make it. Looking forward to seeing you all!