3 code implementations • NeurIPS 2019 • Koen Helwegen, James Widdicombe, Lukas Geiger, Zechun Liu, Kwang-Ting Cheng, Roeland Nusselder
Together, the redefinition of latent weights as inertia and the introduction of Bop enable a better understanding of BNN optimization and open up the way for further improvements in training methodologies for BNNs.
no code implementations • ICLR 2018 • Davide Zambrano, Isabella Pozzi, Roeland Nusselder, Sander Bohte
These adaptive spiking neurons implement an adaptive form of sigma-delta coding to convert internally computed analog activation values to spike-trains.
no code implementations • 13 Oct 2017 • Davide Zambrano, Roeland Nusselder, H. Steven Scholte, Sander Bohte
Adaptive spike-time coding additionally allows for the dynamic control of neural coding precision: we show how a simple model of arousal in AdSNNs further halves the average required firing rate and this notion naturally extends to other forms of attention.