The enticing new title courtesy of Packt Publishing, “Machine Learning with PyTorch and Scikit-Learn,” by Sebastian Raschka, Yuxi (Hayden) Liu, and Vahid Mirjalili is a welcome addition to any data scientist’s list of learning resources. This 2022 tome consists of 741 well-crafted pages designed to provide a comprehensive framework for working in the realm of machine learning and deep learning. The book is brimming over with topics that will propel you to a leading-edge understanding of the field. Topical areas include an introduction to ML including a simple implementation of perceptron algorithm, data munging, dimensionality reduction, a tour of classification algorithms (logistic regression, SVM, decision tree, KNN), model evaluation and hyperparameter tuning, ensemble learning, regression, sentiment analysis, and unsupervised learning with clustering.
The book then shifts into high gear with a number of contemporary topics in deep learning, all using the popular PyTorch framework: implementing a simple multi-layer ANN, parallelizing neural network training, image classification with CNNs, modeling sequential data with RNNs, transformers and NLP, GANs, graph neural networks, and reinforcement learning. A very comprehensive book indeed!
The book is the new member of Packt’s ML series that includes a 2019 title I reviewed a couple of years ago: “Python Machine Learning, 3rd Edition.” The two books have largely the same content with one big exception, the previous book was based on TensorFlow for deep learning topics, while this one uses PyTorch (the clear winner today with deep learning projects; just look at the code associated with papers appearing on arXiv).
The new book picked up a third author Liu, and added two new chapters – transformers and graph neural networks. The previous book’s chapter on embedding an ML model into a web app was removed. The new book has reworked versions of all the previous book’s chapters, making the content even more compelling, and clearly more refined. I was a huge fan of the 2019 book and recommended it to all my Intro to Data Science students at UCLA; I intend to do the same with this new book.
One big attraction of this book is how it streamlines the integration of fundamentals and mathematics/statistics for many important elements of machine learning. This theoretical content is then integrated with a generous degree of Python code found throughout the book. The quality and style of the code is also top rate. Jupyter notebooks for each chapter’s code can be found at a GitHub site designed as a resource for supplemental content.
My favorite chapter in the book is Chapter 3 – A Tour of Machine Learning Classifiers Using Scikit-Learn. This is a great chapter for beginners because it provides a well-rounded look at many useful techniques in machine learning. After reading this one chapter, you can instantly solve many problems in data science.
There are many excellent choices from the inventory of new books on the market today for kick-starting your machine learning skill-set. This new book should definitely occupy a place at the top of the list. You should consider using this book as a learning resource for developing your data science superpowers. Highly recommended!
Contributed by Daniel D. Gutierrez, Editor-in-Chief and Resident Data Scientist for insideAI News. In addition to being a tech journalist, Daniel also is a consultant in data scientist, author, educator and sits on a number of advisory boards for various start-up companies.
Sign up for the free insideAI News newsletter.
Join us on Twitter: @InsideBigData1 – https://twitter.com/InsideBigData1
Speak Your Mind