References: How machines see: convolution

Source material

Source curriculum (structural mirror, cited as further study):
• MIT 6.S191, "Introduction to Deep Learning", Lecture 3: "Deep Computer Vision"
  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 3: Deep Computer Vision by Alexander and Ava Amini. The lecture this lesson mirrors. It animates the filter sliding across an image and shows real feature maps lighting up on edges and textures. Watching the convolution move is the fastest way to make the hand-worked edge detector here feel alive.

Going deeper

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

• Stanford CS231n notes: Convolutional Neural Networks. The canonical course notes on convnets, careful and complete: filter sizes, stride, padding, and how the output dimensions work out. The natural deeper read once the single-filter idea here has landed and you want the full layer specified precisely.

• The MIT 6.S191 software labs. The computer-vision lab is where you can run a real convolutional network on images and watch what its filters learn to detect. MIT-licensed; the hands-on companion to this lesson.

Adjacent topics

Where this connects inside the track.

• Attention and transformers, in brief (lesson 3). The previous lesson closed the sequence phase. This lesson opens the vision phase with the convolution, the image equivalent of “wire the network to the structure of the data.”

• From edges to objects (lesson 5). This lesson built a single convolution that finds one local pattern. The next lesson stacks convolutions into a hierarchy, edges feeding into corners and curves, those into parts, parts into whole objects, and shows how that layered build-up turns local patterns into recognition.