Computer Vision

Turning pixels into structure. Filtering and features, convolutional models, and the geometry that relates an image to the scene behind it.

5 items

Learning paths (1)

Deep Learning Foundations

What a neural network actually computes, how the chain rule delivers every gradient in one backward sweep, and why convolution is the right prior for an image.

Encyclopedia (1)

Convolutional Neural Network

A neural network that applies learned filters across an input’s spatial extent, sharing weights so the same pattern is detected wherever it occurs.

Articles (1)

Convolutional Networks for Vision

Convolution defined properly, a Sobel edge detector worked by hand on a 5x5 image, why sliding one small kernel over an image beats a dense layer by five orders of magnitude in parameters, and what changed when kernels stopped being designed and started being learned.

Datasets (1)

MNIST handwritten digits

70,000 labelled images of handwritten digits - the standard first test that a neural network implementation works at all.

Research (1)

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Applies a standard transformer directly to images by cutting each image into fixed-size patches and treating the sequence of patches as tokens, with no convolutions.