Skip to Main Content
Python Deep Learning Projects
book

Python Deep Learning Projects

by Matthew Lamons, Rahul Kumar, Abhishek Nagaraja
October 2018
Intermediate to advanced content levelIntermediate to advanced
472 pages
10h 57m
English
Packt Publishing
Content preview from Python Deep Learning Projects

DS2 model description and intuition

DS2 architecture is composed of many layers of recurrent connections, convolutional filters, and non-linearities, as well as the impact of a specific instance of batch normalization, applied to RNNs, as shown here:

To learn from datasets with a large amount of data, DS2 model's capacity is increased by adding more depth. The architectures are made up to 11 layers of many bidirectional recurrent layers and convolutional layers. To optimize these models successfully, batch normalization for RNNs and a novel optimization curriculum called SortaGrad were used.

The training data is a combination of input sequence ...

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

Hands-On Python Deep Learning for the Web

Hands-On Python Deep Learning for the Web

Anubhav Singh, Sayak Paul

Publisher Resources

ISBN: 9781788997096Supplemental Content