dot product attention - Robuta Search

https://openreview.net/forum?id=ewQlC1ZpWi Symmetric Dot-Product Attention for Efficient Training of BERT Language Models | OpenReview Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with... dot product attention https://deepai.org/publication/capsules-with-inverted-dot-product-attention-routing Capsules with Inverted Dot-Product Attention Routing | DeepAI Feb 12, 2020 - 02/12/20 - We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement ... dot product attention capsules inverted routing deepai