Andrej Karpathy's Course: Building Neural Networks from Scratch to GPT
By
suioir
4mo ago· 1 min readen
38/100
Stale
Bagelometer↗
Even the toaster can't save this one.
Score38Typehow-toSentimentpositive
Summary
Andrej Karpathy offers a course teaching how to build neural networks from scratch in code, starting with backpropagation basics and progressing to modern deep neural networks like GPT. The course focuses on language models as an excellent learning platform for deep learning fundamentals that transfer to other areas like computer vision. Prerequisites include solid Python programming skills and introductory-level mathematics.
Key quotes
· 4 pulledWe start with the basics of backpropagation and build up to modern deep neural networks, like GPT.
In my opinion language models are an excellent place to learn deep learning, even if your intention is to eventually go to other areas like computer vision because most of what you learn will be immediately transferable.
This is why we dive into and focus on language models.
Prerequisites: solid programming (Python), intro-level math (e.g. derivative, gaussian).
A course by Andrej Karpathy on building neural networks, from scratch, in code.
