Using Swift as a Language for Machine Learning

The idea is indeed a differentiable programming. So what you tend to do a lot in modern machine learning is doing gradient descent. And having the ability to compute the derivative there is very, a very powerful thing. If you have a model that has millions of parameters, you don't want to compute the gradient numerically. That's where a differential programming is actually very helpful.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.