HIGHLIGHTS
- who: Michael E., Rule and Martino, Sorbaro from the Institute for Adaptive and Neural Computation, School of Informatics, University of Edinburgh, Edinburgh , AB, UK have published the research work: Optimal Encoding in Stochastic Latent-Variable Models, in the Journal: Entropy 2020, 22, 714 of /2020/
- what: The authors explore encoding strategies learned by statistical models of sensory coding in noisy spiking networks. By examining a thermodynamics interpretation of the RBM, the authors show that statistical criticality connects to the optimization of the underlying network parameters, and that it suggests an optimal model size that balances . . .
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.