Week 1 Part I · Foundations
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.
MIT's free open course; Lecture 1 lays out what deep learning is and the foundations of neural networks.
Frames every ML task in terms of data, model, objective (loss), and optimization, exactly the framing this week teaches.
A visual, intuition-first introduction to neural networks using the MNIST digit example.
Shows how a model plus loss becomes a computational graph whose derivatives are computed efficiently.