LAUSR

Preserving activations in recurrent neural networks based on surprisal

Sign Up to like & get
recommendations!
0 Published in 2019 at "Neurocomputing"

DOI: 10.1016/j.neucom.2018.11.092

Abstract: Abstract Learning hierarchical abstractions from sequences is a challenging and open problem for recurrent neural networks (RNNs). This is mainly due to the difficulty of detecting features that span over long time distances with also… read more here.

Keywords: activations recurrent; neural networks; preserving activations; recurrent neural ... See more keywords