Introduction to Deep Learning · HIT

Week 1   Part I · Foundations

Deep Learning Overview & ML-to-Network Framing

What deep learning is; framing a task as tensor inputs, model outputs, and a loss function.

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
MIT 6.S191: Introduction to Deep Learning introtodeeplearning.com

MIT's free open course; Lecture 1 lays out what deep learning is and the foundations of neural networks.

Book
Dive into Deep Learning, Chapter 1: Introduction d2l.ai

Frames every ML task in terms of data, model, objective (loss), and optimization, exactly the framing this week teaches.

Video
3Blue1Brown: But what is a neural network? 3blue1brown.com

A visual, intuition-first introduction to neural networks using the MNIST digit example.

Blog / Docs
Colah's blog: Calculus on Computational Graphs (Backpropagation) colah.github.io

Shows how a model plus loss becomes a computational graph whose derivatives are computed efficiently.

← Back to the Week 1 lab

NextWeek 2: Tensors & Data Representation