Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python

by Sebastian Raschka, Yuxi (Hayden) Liu, Vahid Mirjalili

This book of the bestselling and widely acclaimed Python Machine Learning series is a comprehensive guide to machine and deep learning using PyTorch's simple to code framework. Purchase of the print or Kindle book includes a free eBook in PDF format. Machine Learning with PyTorch and Scikit-Learn is a comprehensive guide to machine learning and deep learning with PyTorch. It acts as both a step-by-step tutorial and a reference you'll keep coming back to as you build your machine learning systems. Packed with clear explanations, visualizations, and examples, the book covers all the essential machine learning techniques in depth. While some books teach you only to follow instructions, with this machine learning book, we teach the principles allowing you to build models and applications for yourself. Why PyTorch? PyTorch is the Pythonic way to learn machine learning, making it easier to learn and simpler to code with. This book explains the essential parts of PyTorch and how to create models using popular libraries, such as PyTorch Lightning and PyTorch Geometric. You will also learn about generative adversarial networks (GANs) for generating new data and training intelligent agents with reinforcement learning. Finally, this new edition is expanded to cover the latest trends in deep learning, including graph neural networks and large-scale transformers used for natural language processing (NLP). This PyTorch book is your companion to machine learning with Python, whether you're a Python developer new to machine learning or want to deepen your knowledge of the latest developments. If you have a good grasp of Python basics and want to start learning about machine learning and deep learning, then this is the book for you. This is an essential resource written for developers and data scientists who want to create practical machine learning and deep learning applications using scikit-learn and PyTorch. Before you get started with this book, you'll need a good understanding of calculus, as well as linear algebra. (N.B. Please use the Look Inside option to see further chapters)

Genres: Programming, Artificial Intelligence, Computer Science, Technical, Technology, Textbooks, Nonfiction

770 pages, Paperback

Published February 25, 2022

About the author

Some of my greatest passions are "Data Science" and machine learning. I enjoy everything that involves working with data: The discovery of interesting patterns and coming up with insightful conclusions using techniques from the fields of data mining and machine learning for predictive modeling.

I am a big advocate of working in teams and the concept of "open source." In my opinion, it is a positive feedback loop: Sharing ideas and tools that are useful to others and getting constructive feedback that helps us learn!

A little bit more about myself: Currently, I am sharpening my analytical skills as a PhD candidate at Michigan State University where I am currently working on a highly efficient virtual screening software for computer-aided drug-discovery and a novel approach to protein ligand docking (among other projects). Basically, it is about the screening of a database of millions of 3-dimensional structures of chemical compounds in order to identifiy the ones that could potentially bind to specific protein receptors in order to trigger a biological response.

In my free-time I am also really fond of sports: Either playing soccer or tennis in the open air or building models for predictions. I always enjoy creative discussions, and I am happy to connect with people. Please feel free to contact me by email or in one of those many other networks!

Reviews

[Yogesh · Rating 5 out of 5]

Great intermediate level book, covers broad range of topics including decent chapters on GAN, GNN and RL.

More math than some other entry level books though not as much math as ESL or Bishop, this books is more inclined towards practical aspects.

[Zahra Dashti · Rating 4 out of 5]

‍ #کتاب Machine Learning with PyTorch and Scikit-Learn تألیف Sebastian Raschka یکی از جامع‌ترین منابع موجود برای یادگیری مباحث machine learning و deep learning با تمرکز بر پیاده‌سازی عملی در زبان Python است. این کتاب با ترکیب دو کتابخانه‌ی پرکاربرد Scikit-Learn و PyTorch، مخاطب را از مفاهیم پایه‌ای تا سطوح پیشرفته هدایت می‌کند.
سرفصل‌های اصلی کتاب شامل موارد زیر است:
مبانی supervised و unsupervised learning
الگوریتم‌های کلاسیک مانند logistic regression، decision trees و support vector machines
تکنیک‌های ارزیابی مدل نظیر cross-validation، ROC curves و confusion matrix
پردازش داده‌ها و feature engineering
ساخت و آموزش neural networks با استفاده از PyTorch
پیاده‌سازی مدل‌های پیشرفته شامل CNNs، RNNs و transformers
آموزش مدل‌ها روی GPU و نحوه‌ی آماده‌سازی داده‌های سفارشی
معرفی مقدماتی به model deployment و بهینه‌سازی مدل
این کتاب برای افرادی مناسب است که آشنایی مقدماتی با زبان Python دارند و علاقه‌مند هستند دانش خود را در حوزه‌ی machine learning گسترش دهند. چه برای دانشجویان، چه توسعه‌دهندگان نرم‌افزار و چه پژوهشگران، این کتاب می‌تواند یک مسیر یادگیری مؤثر و منسجم فراهم کند.

نقاط قوت:
توضیح مفاهیم به‌صورت مرحله به مرحله و قابل فهم
پوشش هم‌زمان الگوریتم‌های کلاسیک و مدل‌های مبتنی بر deep learning
ارائه‌ی مثال‌های کدنویسی عملی با قابلیت اجرا
انسجام ساختار مطالب از مبانی تا پیاده‌سازی پیشرفته
نقاط ضعف:
نیاز به آشنایی اولیه با مفاهیم ریاضی پایه در برخی فصل‌ها
حجم بالای برخی فصل‌ها ممکن است برای مطالعه‌ی پیوسته چالش‌برانگیز باشد
اجرای برخی مثال‌ها نیاز به منابع سخت‌افزاری مناسب (مانند GPU) دارد

مطالعه‌ی این کتاب تجربه‌ی بسیار ارزشمندی برای من بود. به کمک آن توانستم درک دقیق‌تری از نحوه‌ی کار الگوریتم‌های یادگیری ماشین و ساختارهای deep learning پیدا کنم. پیاده‌سازی گام‌به‌گام مثال‌ها در کنار توضیحات دقیق، باعث شد مطالب به‌خوبی برایم جا بیفتد و در پروژه‌های شخصی نیز مورد استفاده قرار گیرد.
به‌ویژه بهره‌گیری از هر دو کتابخانه‌ی Scikit-Learn و PyTorch این امکان را فراهم کرد تا درک بهتری از تفاوت‌ها، مزایا و کاربردهای هر یک داشته باشم.
در مجموع، این کتاب را به همه‌ی علاقه‌مندان جدی به machine learning که قصد دارند از سطح تئوری فراتر بروند و وارد فاز عملیاتی شوند، توصیه می‌کنم.

[Ismail Cetin · Rating 5 out of 5]

This book focuses on the modern deep learning algorithms and how can we implement beginner level Deep Learning algorithms. It touches on every subject and provides a 3-4 page code snippets which do not take so much time to code up and you can see the immediate result. I love the fluency of the language (it was easy to understand) as well as the comprehensiveness of the book. You should definitely buy it if you have the money and read it if you are a beginner to Deep Learning field. Python knowledge as it is stated on foreword of the book is necessary but as a fourth year student computer engineer student from Istanbul Technical University, it makes me feel I am capable of writing a deep-learning algorithm from scratch.

[Özgür · Rating 3 out of 5]

Good book with a lot of content...
Book digresses too much to include too much impractical content have for the sake of completeness...
e.g. writing scikitlearn methods with python from scratch. Too much of a waste of readers time.

[Marian · Rating 4 out of 5]

Very useful

[Derek Bridge · Rating 5 out of 5]

Sebstian is a dedicated and tireless educator, as this excellent 700+ page tome demonstrates. Recommended.

[Siyuan LIU · Rating 4 out of 5]

clear explanations but too plain and entry level

[Simon · Rating 5 out of 5]

The book is a complete introduction to the field of machine learning and deep learning. It is very math heavy, but has very good explanations.

[Si Mokrane · Rating 5 out of 5]

Essential for modern environmental modeling workflows.

[Travis Jones · Rating 5 out of 5]

This book is very thorough and has a plethora of supplemental information. The author was a professor and has some great external resources that can guide any level of learner to a better understanding of the material. Although some of book is a little basic, if you take your time with it there is a lot of value to be extracted. Enjoyed!!!

[Jonas Buro · Rating 4 out of 5]

Good beginner/intermediate text. Provides a Scikit-Learn tour through classical machine learning algorithms such as perceptron, SVMs, decision trees, and k-nearest neighbours. Gives a decent overview of the machine learning pipeline, from data acquisition to model evaluation. The second half introduces Pytorch, and covers briefly some modern techniques such as GNNs and GANs.

[John Y · Rating 4 out of 5]

Overall good book with detail coding. Lot of math ..