Introduction to Deep Learning · HIT

Week 3   Part I · Foundations

MLPs & Backpropagation

Multilayer perceptrons; the forward pass; backpropagation mechanics via PyTorch autograd.

Curated, free, canonical references for this week: a course or lecture, a book chapter, a video, and an authoritative blog post or official tutorial. Each opens in a new tab.

Course
Karpathy: The spelled-out intro to neural networks and backpropagation (micrograd) youtube.com

Builds an MLP and a tiny autograd engine from scratch, deriving the forward pass and backprop step by step.

Book
Dive into Deep Learning, 5.1 Multilayer Perceptrons d2l.ai

Introduces hidden layers and nonlinear activations and why MLPs go beyond linear models.

Video
3Blue1Brown: Backpropagation, intuitively 3blue1brown.com

A visual walkthrough of how gradients flow backward through a network to update weights.

Blog / Docs
PyTorch Official Tutorial: A Gentle Introduction to torch.autograd docs.pytorch.org

Connects backprop theory to PyTorch autograd: the dynamic graph, requires_grad, and .backward().

← Back to the Week 3 lab

PreviousWeek 2: Tensors & Data RepresentationNextWeek 4: Data Pipelines