You're reading from Python Machine Learning by Example Build intelligent systems using Python, TensorFlow 2, PyTorch, and scikit-learn

Product type Paperback

Published in Oct 2020

Publisher Packt

ISBN-13 9781800209718

Length 526 pages

Edition 3rd Edition

Languages

Python

Tools

PyTorch

Concepts

Machine Learning

Author (1):

Yuxi (Hayden) Liu

View More author details

Table of Contents (17) Chapters

Preface

1. Getting Started with Machine Learning and Python

2. Building a Movie Recommendation Engine with Naïve Bayes FREE CHAPTER

3. Recognizing Faces with Support Vector Machine

4. Predicting Online Ad Click-Through with Tree-Based Algorithms

5. Predicting Online Ad Click-Through with Logistic Regression

6. Scaling Up Prediction to Terabyte Click Logs

7. Predicting Stock Prices with Regression Algorithms

8. Predicting Stock Prices with Artificial Neural Networks

9. Mining the 20 Newsgroups Dataset with Text Analysis Techniques

10. Discovering Underlying Topics in the Newsgroups Dataset with Clustering and Topic Modeling

11. Machine Learning Best Practices

12. Categorizing Images of Clothing with Convolutional Neural Networks

13. Making Predictions with Sequences Using Recurrent Neural Networks

14. Making Decisions in Complex Environments with Reinforcement Learning

15. Other Books You May Enjoy

16. Index

Advancing language understanding with the Transformer model

The Transformer model was first proposed in Attention Is All You Need (https://arxiv.org/abs/1706.03762). It can effectively handle long-term dependencies, which are still challenging in LSTM. In this section, we will go through the Transformer's architecture and building blocks, as well as its most crucial part: the self-attention layer.

Exploring the Transformer's architecture

We'll start by looking at the high-level architecture of the Transformer model (image taken from Attention Is All You Need):

Figure 13.15: Transformer architecture

As you can see, the Transformer consists of two parts: the encoder (the big rectangle on the left-hand side) and the decoder (the big rectangle on the right-hand side). The encoder encrypts the input sequence. It has a multi-head attention layer (we will talk about this next) and a regular feedforward layer. On the other hand, the decoder...