CNN

Overview

A convolutional neural network applies the same small filter at every position of an input, so it learns a pattern once and recognises it anywhere. It solves the parameter explosion that a fully connected layer would suffer on an image, where each pixel would need its own weight. It exists because locality and translation invariance are true of images and largely untrue of language, which is why vision and language ended up with different architectures.

Technology Graph

How CNN connects to the rest of the stack.

Alternatives

• ViT architecture

  An alternative to CNN · source

Comparisons

Side-by-side breakdowns with the alternatives above.

• CNN vs ViT