Adaptive Computation Time for Recurrent Neural Networks
arXiv: Neural and Evolutionary Computing, Volume abs/1603.08983, 2016.
This paper introduces Adaptive Computation Time (ACT), an algorithm that allows recurrent neural networks to learn how many computational steps to take between receiving an input and emitting an output. ACT requires minimal changes to the network architecture, is deterministic and differentiable, and does not add any noise to the paramete...More
PPT (Upload PPT)