References: Why seeing is hard for machines

Source material

This track is a structural mirror of Stanford’s CS231n. The lessons are original Clawdemy prose; the course is cited as the curriculum we follow and recommend for deeper study.

• Course: Stanford CS231n, “Deep Learning for Computer Vision”
• Instructors: Fei-Fei Li, Ehsan Adeli, and Justin Johnson (Stanford University)
• Course site: cs231n.stanford.edu
• This lesson maps to: Lecture 1 (Introduction) and the image-classification framing that opens the course.

Attribution (Clawdemy-authored): Stanford CS231n: Deep Learning for Computer Vision, Fei-Fei Li, Ehsan Adeli, and Justin Johnson, Stanford University (cs231n.stanford.edu). CS231n does not publish a required citation string; this is the attribution Clawdemy uses.

A note on access and license

The current term’s lecture recordings are posted on Canvas for enrolled Stanford students. Recordings from previous years are publicly available on YouTube under YouTube’s standard license; Clawdemy links out to source material rather than embedding or rehosting it. The course notes and site are Stanford’s. No Creative Commons license is published for the lectures, so we treat them as link-only references.

Further study

• The CS231n lecture series. Prior-year recordings are on YouTube; search for “Stanford CS231n” to find the lecture videos, and the course site above for the schedule and notes.
• Neural Network Intuition (Track 11, Clawdemy). The handwritten-digit problem there is a small grayscale version of the recognition task this track scales up to color, real-world images.
• Introduction to Deep Learning (Track 12, Clawdemy). A broader survey of deep learning, including a lesson on convolution that this track develops in depth.

How we use this source

Clawdemy follows CS231n’s pedagogical arc and topic ordering, then writes its own explanations, examples, and practice. We do not reproduce the course’s slides, figures, problem sets, or lecture text. Where a specific idea or example originates with the course, the lesson says so. Full attribution policy: see Doc/attribution-policy.md.