no code implementations • 5 Oct 2021 • Narsimha Chilkuri, Eric Hunsberger, Aaron Voelker, Gurshaant Malik, Chris Eliasmith
Over three orders of magnitude, we show that our new architecture attains the same accuracy as transformers with 10x fewer tokens.
2 code implementations • NeurIPS 2019 • Aaron Voelker, Ivana Kajić, Chris Eliasmith
Backpropagation through the ODE solver allows each layer to adapt its internal time-step, enabling the network to learn task-relevant time-scales.
Ranked #12 on Sequential Image Classification on Sequential MNIST