Dec 12, 2025 · 5 min read · To understand autograd, it’s important to first understand two key concepts: gradients and computation graphs. Let’s go through them step-by-step. What is Gradient Descent ? Gradient descent is an optimization algorithm used to minimize a loss functi...
Join discussion
Nov 18, 2025 · 7 min read · Why I Built My Own Deep Learning Framework? After watching Andrej Karpathy’s micrograd lecture, I had a realization: I’d been using PyTorch for months, but I didn’t really understand how autograd worked. Sure, I could call .backward() and get gradien...
Join discussionMar 23, 2025 · 3 min read · Autograph: PyTorch's autograd engine is the magic behind automatic differentiation. As machine learning engineers or deep learning practitioners, we often define a loss function and expect our framework to figure out how to update weights. PyTorch ha...
Join discussion