divergences
  • Posts
  • Topics
  • Archive
  • About

Tag

CNN

All topics

2 posts RSS feed for this page

  1. 2023
  2. 2023-03-27 14 min en

    Implementing rotation equivariance: Group-equivariant CNN from scratch

    We code up a simple group-equivariant convolutional neural network (GCNN) that is equivariant to rotation. The world may be upside down, but the network will know.

    Deep LearningGeometric Deep Learning
  3. 2023-03-09 10 min en

    Upside down, a cat's still a cat: Evolving image recognition with Geometric Deep Learning

    In this first in a series of posts on group-equivariant convolutional neural networks (GCNNs), meet the main actors — groups — and concepts (equivariance). With GCNNs, we finally revisit the topic of Geometric Deep Learning, a principled, math-driven approach to neural networks that has consistently been rising in scope and impact.

    Deep LearningGeometric Deep Learning
No matching items
Back to top

A blog by Sigrid Keydana. Opinions are exclusively mine.

 
  • RSS

  • Archive