Python Machine Learning By Example

Learn machine learning (ML) with this hands-on guide from best-selling author and ex-Google ML engineer Yuxi (Hayden) Liu. He teaches the basics of ML algorithms to NLP transformers and multimodal models with best practice tips and real-world examples

Key Features

New and updated content on NLP transformers, PyTorch, and computer vision modeling
Best practices have expanded beyond one chapter with tips to improve your ML solutions showcased throughout the book
Implement ML algorithms, such as neural networks and decision trees from scratch

Book DescriptionThe fourth edition of Python Machine Learning by Example is a comprehensive guide for beginners and experienced ML practitioners who want to learn more advanced techniques like multimodal modeling. Written by best-selling author and ex-Google ML engineer Yuxi (Hayden) Liu, this edition emphasizes best practices, providing invaluable insights for ML engineers, data scientists, and analysts.

Explore advanced techniques, including two new chapters on NLP transformers with BERT and GPT-4 and multimodal computer vision models with PyTorch and Hugging Face. You’ll learn advanced modeling techniques using practical examples, such as predicting stock prices and creating an image search engine.

This book navigates through complex challenges, bridging the gap between theoretical understanding and practical application. Elevate your ML expertise, tackle intricate problems, and unlock the potential of advanced techniques in machine learning with this authoritative guide.What you will learn

Follow machine learning best practices for data preparation, model training, and evaluation
Build and improve image classifiers using CNNs, transfer learning, and data augmentation
Build and fine-tune neural networks using TensorFlow and PyTorch for stock price prediction and image search
Analyze sequence data and make predictions using RNNs and transformers
Build classifiers using SVMs and boost performance with principal component analysis
Learn to avoid overfitting using cross-validation, regularization, feature selection, and dimensionality reduction

Who this book is forThis expanded fourth edition is ideal for data scientists, ML engineers, analysts, and students with Python knowledge. The real-world lessons and code prepare anyone undertaking their first serious ML project.