This course by Andrej Karpathy is a step-by-step guide to building neural networks from scratch, starting with backpropagation and building up to modern deep neural networks like GPT. The focus is on language models, which are an excellent place to start for learning deep learning. The prerequisites are solid programming (Python) and intro-level math (e.g. derivative, gaussian). The course covers backpropagation, language modeling, multilayer perceptrons, activations and gradients, BatchNorm, and building a WaveNet. With this course, youll gain competence and intuition around how neural nets are optimized and confidently innovate on and debug modern neural networks.
