Synaptic balancing: a biologically plausible local learning rule that provably increases neural network noise robustness without sacrificing task performance

HIGHLIGHTS

• who: Christopher H. Stock and colleagues from the Neuroscience Graduate Program, Stanford University School of Medicine, Stanford, California, United States of America, Department of Applied Physics, Stanford University, Stanford, California, United States have published the paper: Synaptic balancing: A biologically plausible local learning rule that provably increases neural network noise robustness without sacrificing task performance, in the Journal: (JOURNAL) of September/19,/2022
• what: This work provides novel practical local learning rule that exactly preserves overall network function and in the mathematics of integrable Lax dynamical systems. The main contribution is the discovery of a . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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