HIGHLIGHTS
- who: Anthony Strock and colleagues from the INRIA Bordeaux Sud-Ouest, Bordeaux, France have published the research: A Robust Model of Gated Working Memory, in the Preprint: biorxiv
- what: The authors propose instead to consider an implicit mechanism based on a random recurrent neural network. A deeper study of the model shows that there is actually a large range of hyper parameters for which the results hold (number of neurons sparsity global weight scaling etc.) such that any large enough population mixing excitatory and inhibitory neurons can quickly learn to realize such gated working memory . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.