References: What deep learning adds

Source material

Source curriculum (structural mirror, cited as further study):
• MIT 6.S191, "Introduction to Deep Learning", Lecture 1
  Instructors: Alexander Amini and Ava Amini (MIT)
  Course page: https://introtodeeplearning.com
  Code and labs: https://github.com/aamini/introtodeeplearning
  License: MIT (slides, code, and labs); videos are YouTube standard
  Required attribution: "© Alexander Amini and Ava Amini, MIT 6.S191:
    Introduction to Deep Learning, IntroToDeepLearning.com"
Clawdemy's lessons are original prose that follows the pedagogical arc of this
course. We do not reproduce or transcribe the lectures; we cite them as the
recommended companion. Course materials are used under their MIT license with
the attribution above; all rights to the original videos remain with the creators.

Watch this next

• MIT 6.S191, Lecture 1: Introduction to Deep Learning by Alexander and Ava Amini. The lecture this lesson mirrors, freely available from the course page. It covers this same orientation with the instructors’ own framing and animations, and the course is refreshed every year, so it is also the best place to see the most current version of the “why now” story. The opening lecture is the natural watch alongside this lesson.

Going deeper

A short, durable list. Each link is a specific next step, not a generic pile.

• “ImageNet Classification with Deep Convolutional Neural Networks” (Krizhevsky, Sutskever, and Hinton, 2012). The AlexNet paper, the primary source for the 2012 moment this lesson describes. If you want to see exactly what won ImageNet and the numbers behind it (the layers, the parameters, the training setup), this is where it was first reported.

• The MIT 6.S191 software labs. The course’s hands-on notebooks, MIT-licensed. Even if you only skim them now, knowing they exist is useful: as the track introduces each architecture, the matching lab is where you can run it yourself.

Adjacent topics

Where this connects.

• Neural network intuition (the previous track). This lesson assumed you know what a neural network is and how it learns. If “layers, weights, gradient descent, backpropagation” did not all feel familiar, that track is the engine this whole track builds vehicles around.

• Why sequences need memory (lesson 2). The tour begins with the first problem shape. The next lesson explains why a plain feedforward network struggles with ordered data, and how giving a network memory lets it carry information from one step to the next.