Naturally Occurring Equivariance in Neural Networks

Neural networks naturally learn many transformed copies of the same feature, connected by symmetric weights.

Naturally Occurring Equivariance in Neural Networks Naturally Occurring Equivariance in Neural Networks Distill { "title": "Naturally Occurring Equivariance in Neural Networks", "description": "Neural networks naturally learn many transformed copies of the same feature, connected by symmetric weights.", "authors": [ { "author": "Chris Olah", "authorURL": "https://colah.github.io", "affiliation": "OpenAI", "affiliationURL": "https://openai.com" }, { "author": "Nick Cammarata", "authorURL": "http://nickcammarata.com", "affiliation": "OpenAI", "affiliationURL": "https://openai.com" }, { "author":

saved by

• Noah T
• Davis Brown
• Alexander Davies

related reading

• Scale-invariant-CNNs/docs/Report/Implementation.md at master · ruoqizzz/Scale-invariant-CNNs · GitHubgithub.com
• Feature-wise transformationsdistill.pub
• Zoom In: An Introduction to Circuitsdistill.pub
• Feature Visualizationdistill.pub
• 10. Equivariant Neural Networks — deep learning for molecules & materialsdmol.pub
• Verifying your browser | OpenReviewopenreview.net
• [1411.5908] Understanding image representations by measuring their equivariance and equivalencearxiv.org
• Multimodal Neurons in Artificial Neural Networksdistill.pub
• Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
• CS231n Deep Learning for Computer Visioncs231n.github.io
• Toy Models of Superpositiontransformer-circuits.pub
• Analogies between Biology and Deep Learning [rough note] -- colah's blogcolah.github.io