Skip to content

Instantly share code, notes, and snippets.

@nikos-kekatos

nikos-kekatos/nnec.md

Created July 28, 2023 11:43
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save nikos-kekatos/0d297b5a5c4fe905a5e25c2bdd09c2e1 to your computer and use it in GitHub Desktop.
Save nikos-kekatos/0d297b5a5c4fe905a5e25c2bdd09c2e1 to your computer and use it in GitHub Desktop.
Download ZIP
Neural Network Equivalence
Raw
nnec.md

Useful/Relevant Papers or applications

Unorganized

  1. SIMILARITY OF NEURAL NETWORK MODELS: A SURVEY OF FUNCTIONAL AND REPRESENTATIONAL MEASURES https://arxiv.org/pdf/2305.06329.pdf
metrics to check a) how much  hidden layers differ (representational similarity), and 
b) how much outputs differ (functional similarity). 

They propose first-order measure (raw outputs/ no activation at the output layer) and
second-order (argmax at output layer).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment