Fetching the paper…
Reading the bibliography…
Recurrent neural networks (RNNs) trained on compositional tasks can exhibit functional modularity, in which neurons can be clustered by activity similarity and participation in shared computational subtasks.
Wiring optimization in cortical circuits
Dmitri B Chklovskii, Thomas Schikorski, and Charles F Stevens · 2002
Earlier work this paper cites.
Maps in the brain: what can we learn from them?
Dmitri B Chklovskii and Alexei A Koulakov · 2004
Earlier work this paper cites.
Wiring optimization can relate neuronal structure and function
Beth L Chen, David H Hall, and Dmitri B Chklovskii · 2006
Cited alongside, same era.
Task representations in neural networks trained to perform many cognitive tasks
Guangyu Robert Yang, Madhura R Joglekar, H Francis Song, William T Newsome, and Xiao-Jing Wang · 2019
Cited alongside, same era.
The localization of function in the brain
David Ferrier
Cited in the paper.
Winning the lottery with neural connectivity constraints: Faster learning across cognitive tasks with spatially constrained sparse rnns
Mikail Khona, Sarthak Chandra, Joy J Ma, and Ila R Fiete · 2023
Closest in time.
Seeing is believing: Brain-inspired modular training for mechanistic interpretability
Ziming Liu, Eric Gan, and Max Tegmark · 2023
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…