flâneur

fast.ai – Providing a Good Education in Deep Learning

fast.ai · 1,746 words · saved by 2 readers

Paul Lockhart, a Columbia math PhD, former Brown professor, and K-12 math teacher, writes in the influential essay A Mathematician’s Lament of a nightmare world where children are not allowed to listen to or play music until they have spent over a decade mastering music notation and theory, spending classes transposing sheet music into a different key. In art class, students study colors and applicators, but aren’t allowed to actually paint until college. Sound absurd? This is how math is taught–we require students to spend years doing rote memorization, and learning dry, disconnected “fundamentals” that we claim will pay off later, long after most of them quit the subject. Unfortunately, this is where several of the few resources on deep learning begin–asking learners to follow along with the definition of the Hessian and theorems for the Taylor approximation of your loss function, without ever giving examples of actual working code. I’m not knocking calculus. I love calculus and have

Providing a Good Education in Deep Learning – fast.ai Paul Lockhart, a Columbia math PhD, former Brown professor, and K-12 math teacher, writes in the influential essay A Mathematician’s Lament of a nightmare world where children are not allowed to listen to or play music until they have spent over a decade mastering music notation and theory, spending classes transposing sheet music into a different key. In art class, students study colors and applicators, but aren’t allowed to actually paint until college. Sound absurd? This is how math is taught–we require students to spend years doing rote

saved by

related reading