Skip to Content
Reinforcement Learning with TensorFlow
book

Reinforcement Learning with TensorFlow

by Sayon Dutta
April 2018
Intermediate to advanced content levelIntermediate to advanced
334 pages
10h 18m
English
Packt Publishing
Content preview from Reinforcement Learning with TensorFlow

Deep residual coattention encoder

Since the original DCN has only one single-layer coattention encoder, the ability to form complex representations of the input sequence is also limited. Thus, two modifications are done to the coattention encoder. They are as follows:

  • Modifying the coattention encoder by stacking many coattention layers so that the network is able to create better complex representation
  • Merging all the coattnetion outputs from each layer to reduce the signal path length:
Deep residual coattention encoder, published in DCN+: Mixed Objective and Deep Residual Coattention for Question Answering(https://arxiv.org/pdf/1711.00106.pdf ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Deep Learning with TensorFlow - Second Edition

Deep Learning with TensorFlow - Second Edition

Giancarlo Zaccone, Vihan Jain, Md. Rezaul Karim, Motaz Saad
Deep Learning with TensorFlow 2 and Keras - Second Edition

Deep Learning with TensorFlow 2 and Keras - Second Edition

Antonio Gulli, Dr. Amita Kapoor, Sujit Pal

Publisher Resources

ISBN: 9781788835725Supplemental Content