Reader small image

You're reading from  Advanced Deep Learning with Python

Product typeBook
Published inDec 2019
Reading LevelIntermediate
PublisherPackt
ISBN-139781789956177
Edition1st Edition
Languages
Right arrow
Author (1)
Ivan Vasilev
Ivan Vasilev
author image
Ivan Vasilev

Ivan Vasilev started working on the first open source Java deep learning library with GPU support in 2013. The library was acquired by a German company, with whom he continued its development. He has also worked as a machine learning engineer and researcher in medical image classification and segmentation with deep neural networks. Since 2017, he has focused on financial machine learning. He co-founded an algorithmic trading company, where he's the lead engineer. He holds an MSc in artificial intelligence from Sofia University St. Kliment Ohridski and has written two previous books on the same topic.
Read more about Ivan Vasilev

Right arrow

Seq2seq with attention

The decoder has to generate the entire output sequence based solely on the thought vector. For this to work, the thought vector has to encode all of the information of the input sequence; however, the encoder is an RNN, and we can expect that its hidden state will carry more information about the latest sequence elements than the earliest. Using LSTM cells and reversing the input helps, but cannot prevent it entirely. Because of this, the thought vector becomes something of a bottleneck. As a result, the seq2seq model works well for short sentences, but the performance deteriorates for longer ones.

Bahdanau attention

We can solve this problem with the help of the attention mechanism (see Neural Machine...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Advanced Deep Learning with Python
Published in: Dec 2019Publisher: PacktISBN-13: 9781789956177

Author (1)

author image
Ivan Vasilev

Ivan Vasilev started working on the first open source Java deep learning library with GPU support in 2013. The library was acquired by a German company, with whom he continued its development. He has also worked as a machine learning engineer and researcher in medical image classification and segmentation with deep neural networks. Since 2017, he has focused on financial machine learning. He co-founded an algorithmic trading company, where he's the lead engineer. He holds an MSc in artificial intelligence from Sofia University St. Kliment Ohridski and has written two previous books on the same topic.
Read more about Ivan Vasilev