Speed Up your AI Code

Learn how to speed up AI code with Christian Hudon, Applied Research Scientist at Element AI. He will talk about how to profile and accelerate a PyTorch model, using Element AI N-Beats as an example. This presentation is perfect for both AI developers who productize models and practitioners who create models and want their training to go faster. It is also meant as a window into how you could dive in head first with AI models at Element AI. Interested in joining our awesome dev team at Element AI? See our job openings here: www.elementai.com/careers. ABOUT CHRISTIAN Githhub: https://github.com/chrish42 When did you learn to code? I learned to code as a kid, starting with BASIC on this thing called a pocket computer — this one, actually: http://oldcomputers.net/trs80pc3.html. My first real computer was a Commodore 64, which was my first real computer. My two other formative early experiences were learning C once we got our first PC, and working through the SICP book for a course dedicated to that book during my bachelors in Computer Engineering. What's your coding pet peeve? Definitely people who write code only for computers and not for their human audiences too. What are your favorite programming languages? My favorite high-level language is still Python, even after 20+ years. It still hits the sweet spot between expressiveness, conciseness, readability and ease of use. What's your go-to coding playlist (or podcast)? Mostly silence, actually. But for the occasions that I do, it's mostly white noise, or baroque classical music. I find most other music too distracting, especially anything with lyrics, or even with too much of a musical "story".