Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Deep Learning with Theano

You're reading from   Deep Learning with Theano Perform large-scale numerical and scientific computations efficiently

Arrow left icon
Product type Paperback
Published in Jul 2017
Publisher Packt
ISBN-13 9781786465825
Length 300 pages
Edition 1st Edition
Tools
Arrow right icon
Author (1):
Arrow left icon
Christopher Bourez Christopher Bourez
Author Profile Icon Christopher Bourez
Christopher Bourez
Arrow right icon
View More author details
Toc

Table of Contents (15) Chapters Close

Preface 1. Theano Basics FREE CHAPTER 2. Classifying Handwritten Digits with a Feedforward Network 3. Encoding Word into Vector 4. Generating Text with a Recurrent Neural Net 5. Analyzing Sentiment with a Bidirectional LSTM 6. Locating with Spatial Transformer Networks 7. Classifying Images with Residual Networks 8. Translating and Explaining with Encoding – decoding Networks 9. Selecting Relevant Inputs or Memories with the Mechanism of Attention 10. Predicting Times Sequences with Advanced RNN 11. Learning from the Environment with Reinforcement 12. Learning Features with Unsupervised Generative Networks 13. Extending Deep Learning with Theano Index

Improving efficiency of sequence-to-sequence network


A first interesting point to notice in the chatbot example is the reverse ordered input sequence: such a technique has been shown to improve results.

For translation, it is very common then to use a bidirectional LSTM to compute the internal state as seen in Chapter 5, Analyzing Sentiment with a Bidirectional LSTM: two LSTMs, one running in the forward order, the other in the reverse order, run in parallel on the sequence, and their outputs are concatenated:

Such a mechanism captures better information given future and past.

Another technique is the attention mechanism that will be the focus of the next chapter.

Lastly, refinement techniques have been developed and tested with two-dimensional Grid LSTM, which are not very far from stacked LSTM (the only difference is a gating mechanism in the depth/stack direction):

Grid long short-term memory

The principle of refinement is to run the stack in both orders on the input sentence as well, sequentially...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at €18.99/month. Cancel anytime