Owen Marschall: Can confirm this was a fun project! My favorite takeaway is that the (low-but-extensive) rank of a network can be used as a knob for controlling dimensionality while leaving single-neuron properties unchanged.

See full post

Owen Marschall omarschall.bsky.social
Can confirm this was a fun project! My favorite takeaway is that the (low-but-extensive) rank of a network can be used as a knob for controlling dimensionality while leaving single-neuron properties unchanged.
- David G. Clark david-g-clark.bsky.social · Nov 3, 2025
  Now in PRX: Theory linking connectivity structure to collective activity in nonlinear RNNs! For neuro fans: conn. structure can be invisible in single neurons but shape pop. activity For low-rank RNN fans: a theory of rank=O(N) For physics fans: fluctuations around DMFT saddle⇒dimension of activity
  Connectivity Structure and Dynamics of Nonlinear Recurrent Neural Networks
  
  The structure of brain connectivity predicts collective neural activity, with a small number of connectivity features determining activity dimensionality, linking circuit architecture to network-level...
  
  journals.aps.org
Nov 4, 2025 15:53
0 reposts 0 quotes 0 likes

View on Bluesky Show all post labels

An unhandled error has occurred. Reload 🗙