EGRU: Event-based GRU for activity-sparse inference and learning. (arXiv:2206.06178v1 [cs.LG] CROSS LISTED)

Web: http://arxiv.org/abs/2206.06178

The scalability of recurrent neural networks (RNNs) is hindered by the
sequential dependence of each time step's computation on the previous time
step's output. Therefore, one way to speed up and scale RNNs is to reduce the
computation required at each time step independent of model size and task. In
this paper, we propose a model that reformulates Gated Recurrent Units (GRU) as
an event-based activity-sparse model that we call the Event-based GRU (EGRU),
where units compute updates only on …

arxiv cross event inference learning lg