The impact of sparsity in low-rank recurrent neural networks

HIGHLIGHTS

• who: Elizabeth Herbert and Srdjan Ostojic from the Laboratoire de Neurosciences Cognitives et Computationnelles, Du00e9partement d`Eu0301tudes Cognitives, INSERM, PSL University, Paris, France have published the research work: The impact of sparsity in low-rank recurrent neural networks, in the Journal: (JOURNAL)
• what: The authors investigate the dynamics of low-rank recurrent networks in which the connections are randomly sparsified which makes the network connectivity formally full-rank. The authors show that both the radius of the eigenvalue bulk and the outliers can be estimated analytically. In Fig 1C the authors demonstrate the correspondence of . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.