| Best Sellers Rank | #39,098 in Books (See Top 100 in Books) #16 in Computer Neural Networks #21 in Natural Language Processing (Books) #22 in Python Programming |
| Customer Reviews | 4.6 out of 5 stars 472Reviews |
We gave the 3rd edition of Python Machine Learning a big overhaul by converting the deep learning chapters to use the latest version of PyTorch. We also added brand-new content, including chapters focused on the latest trends in deep learning. We walk you through concepts such as dynamic computation graphs and automatic differentiation. Additionally, we’ve introduced a popular adversarial training regime for neural networks that can be used to generate new, realistic-looking images.
What’s new:
This book takes you on a journey from the origins of machine learning to the latest deep learning architectures. Through conceptual and practical examples, you'll develop a repertoire of techniques that allow you to solve a wide range of predictive modeling tasks, including tabular, image, and text data.
PyTorch is a very powerful and versatile tool, and deep learning naturally requires very flexible building blocks. Hence, PyTorch can sometimes be very verbose compared to traditional machine learning libraries such as scikit-learn. In this book, we explain how PyTorch works and cover all the essential parts. However, we also focus on code readability to ensure you don’t get overwhelmed.
The book takes a deep dive into the underlying methods and does not shy away from explaining fundamental deep learning architectures and concepts from scratch. Our objective is to teach you deep learning and see how you can put it into practice using PyTorch rather than the other way around.
We put a lot of thought and care into organizing the general structure of the book, the flow of topics, and how the chapters build on each other. This includes the transition from one chapter explaining neural networks by implementing them from scratch in NumPy to another chapter explaining how to use PyTorch to make this more convenient.
There are many great books on machine learning and deep learning out there. However, from many years of teaching and interacting with students, we heard that many books don't include hands-on examples that help readers to put these into practice. Other books have a strong focus on code examples at the expense of explanations. Machine Learning with PyTorch and Scikit-Learn strikes a good balance between concepts, theory, and practice and takes advantage of synergistic effects when explaining new methods.
 Machine Learning with PyTorch and Scikit-Learn |  Mastering Pytorch |  Python Machine Learning |  Python Machine Learning by Example |  Mathematics of Machine Learning | |
|---|---|---|---|---|---|
| Customer Reviews | 472 | 50 | 487 | 51 | 63 |
| Price | $39.95 | $46.79 | $47.77 | $31.11 | $59.99 |
| Technology Used | PyTorch, scikit-learn | PyTorch | TensorFlow, scikit-learn | PyTorch, TensorFlow, pandas, NumPy, scikit-learn | Matplotlib, NumPy, SciPy, scikit-learn |
| Reader Knowledge Level | Beginner to Intermediate | Intermediate to Advanced | Beginner to Intermediate | Beginner to Intermediate | Beginner to Intermediate |
| Topics / New Topics | New content on transformers, gradient boosting, and GNNs | New content on diffusion models, recommender systems, mobile deployment, Hugging Face, and GNNs | Revised and expanded to include GANs and reinforcement learning | Revised with PyTorch builds, expanded best practices, and new content on LLMs and multimodal models | Linear algebra, calculus, multivariable calculus, and probability theory |
