Flux.jl is Julia's elegant machine learning library, but its API is a little different than Tensorflow or PyTorch. This week on Talk Julia, David and Randy dive into Flux.jl, explore some of the big differences between Flux and Python's machine learning libraries, and offer up some tips and tricks for learning Flux if you're coming to it from another ecosystem.

Support Talk Julia on Ko-Fi

We're excited to announce that we have opened up podcast memberships! Become a member for as little as $5/mo to get early access to episodes, social media shoutouts, and, starting at $10/mo and up, access to a members-only "office hours" call.

Your support helps us continue to bring you interviews and educational Julia content each week. It also helps us grow sustainably and improve the quality of the podcast.

Become a member today 👉

Manning Publications Discount

We've partnered with Manning Publications to bring all of our listeners a special 35% discount code on all of Mannings physical books, ebooks, courses, and more. There's no expiration date and you can use the discount as many times as you like!

Just visit http://mng.bz/pOzw and use the code podtalkjulia22 at checkout to get 35% off of your order!

Links:

• Flux.jl GitHub
• Flux.jl Website
• Quick Overview of Flux.jl
• Randy's Flux notebooks
• Flux <3 NumFOCUS — We are very excited to announce that FluxML is partnering with NumFOCUS as an affiliated project to further the cause of open and reproducible science and growing the adoption of the FluxML ecosystem... This partnership will help us in growing the community, bringing new contributors into the ecosystem, and help us manage the funds from future grants we raise for a number of upcoming projects.