When Can Self-Attention Be Replaced by Feed Forward Layers? (2020)
Attributed to:
SpeechWave
funded by
EPSRC
Abstract
No abstract provided
Bibliographic Information
Digital Object Identifier: http://dx.doi.org/10.48550/arxiv.2005.13895
Publication URI: https://arxiv.org/abs/2005.13895
Type: Preprint