Attention Please! The One Little Trick that Improved the State of the Art in Sequence Modelling

Session
This talk originates from the archive. To the CURRENT program
Join the ML Revolution! ✓ Special Discount Register till March 7 and get the Workshop Day for free ✓ Team Discount Register with 3+ colleagues and get 10 % off! Register Now
Infos
Wednesday, June 20 2018
16:15 - 17:15
Room:
Cuvilliés

Attention mechanisms were the key to improving the state of the art in many sequence modelling tasks, like machine translation and image captioning. Besides that, they also allow to make a model more interpretable by showing which sequence elements were the most important when making a decision.
This talk will give you an overview of the different kinds of attention and how they are used. The complex math is skipped in favor of a more intuitive explanation, which should provide you with an understanding of how the different concepts fit together. Finally, a working example of using Deeplearning4J with attention is demonstrated and explained.

Behind the Tracks