Skip to content
Clawdemy

References: Linear classifiers

Source material

Section titled “Source material”

This lesson follows Stanford CS231n’s treatment of linear classification, the canonical entry point into deep learning for vision.

  • Course: Stanford CS231n, “Deep Learning for Computer Vision”
  • Instructors: Fei-Fei Li, Ehsan Adeli, and Justin Johnson (Stanford University)
  • Course site: cs231n.stanford.edu
  • Course notes (this lesson): cs231n.github.io/linear-classify (the canonical write-up of the score function, the template interpretation, the bias trick, and the visualizations of learned CIFAR-10 templates including the famous two-headed horse).
  • This lesson maps to: Lecture 2 (Image Classification with Linear Classifiers).

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

Section titled “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 (cs231n.github.io) and site are Stanford’s. No Creative Commons license is published for the lectures, so we treat them as link-only references.

Further study

Section titled “Further study”
  • CS231n lecture notes on linear classification. cs231n.github.io/linear-classify goes deeper than this lesson into the loss functions (next lesson here) and the explicit visualizations of learned CIFAR-10 templates.
  • CIFAR-10 dataset. cs.toronto.edu/~kriz/cifar.html hosts the 60,000-image benchmark dataset the CS231n linear-classifier results are computed on.
  • Neural Network Intuition (Track 11, Clawdemy). Lesson 3 (Weights, biases, and the squish) defines the same w · x + b per-neuron computation; a linear classifier is the same equation done per-class, before any squishing.

How we use this source

Section titled “How we use this source”

Clawdemy follows CS231n’s pedagogical arc and topic ordering, then writes its own explanations, worked examples, and practice. The numerical example in this lesson’s body (2 by 2 image, 3 classes) is Clawdemy-authored; the CIFAR-10 shape facts and the two-headed-horse observation are taken directly from CS231n’s writeup, cited above. We do not reproduce the course’s slides, figures, problem sets, or lecture text. Full attribution policy: see Doc/attribution-policy.md.