You're reading from Python Machine Learning By Example Unlock machine learning best practices with real-world use cases

Product type Paperback

Published in Jul 2024

Publisher Packt

ISBN-13 9781835085622

Length 518 pages

Edition 4th Edition

Languages

Python

Tools

PyTorch

Concepts

Computer Vision

Author (1):

Yuxi (Hayden) Liu

View More author details

Table of Contents (18) Chapters

Preface

1. Getting Started with Machine Learning and Python

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

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

4. Predicting Online Ad Click-Through with Logistic Regression

5. Predicting Stock Prices with Regression Algorithms

6. Predicting Stock Prices with Artificial Neural Networks

7. Mining the 20 Newsgroups Dataset with Text Analysis Techniques

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

9. Recognizing Faces with Support Vector Machine

10. Machine Learning Best Practices

11. Categorizing Images of Clothing with Convolutional Neural Networks

12. Making Predictions with Sequences Using Recurrent Neural Networks

13. Advancing Language Understanding and Generation with the Transformer Models

14. Building an Image Search Engine Using CLIP: a Multimodal Approach

15. Making Decisions in Complex Environments with Reinforcement Learning

16. Other Books You May Enjoy

17. Index

Generating text using GPT

BERT and GPT are both state-of-the-art NLP models based on the Transformer architecture. However, they differ in their architectures, training objectives, and use cases. We will first learn more about GPT and then generate our own version of War and Peace with a fine-tuned GPT model.

Pre-training of GPT and autoregressive generation

GPT (Improving Language Understanding by Generative Pre-training by Alec Radford et al. 2018) is a decoder-only Transformer architecture, while BERT is encoder only. This means GPT utilizes masked self-attention in the decoders and emphasizes predicting the next token in a sequence.

Think of BERT like a super detective. It gets a sentence with some words hidden (masked) and has to guess what they are based on the clues (surrounding words) in both directions, like looking at a crime scene from all angles. GPT, on the other hand, is more like a creative storyteller. It is pre-trained using an autoregressive language...