Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, 3rd Edition 3rd Edition, Kindle Edition
Use the Amazon App to scan ISBNs and compare prices.
Inspire a love of reading with Prime Book Box for Kids
Discover delightful children's books with Prime Book Box, a subscription that delivers new books every 1, 2, or 3 months — new customers receive 15% off your first box. Learn more.
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
From the Publisher
What's new in this third edition?
Many readers have told us how much they love the first 12 chapters of the book as a comprehensive introduction to machine learning and Python's scientific computing stack. To keep these chapters relevant and to improve the explanations based on reader feedback, we updated them to support the latest versions of NumPy, SciPy, and scikit-learn.
One of the most exciting events in the deep learning world was the release of TensorFlow 2. Consequently, all the TensorFlow-related deep learning chapters have received a big overhaul. Since TensorFlow 2 introduced many new features and fundamental changes, we rewrote these chapters from scratch. Furthermore, we added a new chapter on Generative Adversarial Networks, which are one of the hottest topics in deep learning research, as well as a comprehensive introduction to reinforcement learning based on numerous requests from readers.
What are the key takeaways from your book?
Machine learning can be useful in almost every problem domain. We cover a lot of different subfields of machine learning in the book. My hope is that people can find inspiration for applying these fundamental techniques to drive their research or industrial applications. Also, using well-developed and maintained open source software makes machine learning very accessible to a wide audience of experienced programmers, as well as those who are new to programming.
Python Machine Learning Third Edition is also different from a classic academic machine learning textbook due to its emphasis on practical code examples. However, I think this approach is highly valuable for both students and young researchers who are getting started in machine learning and deep learning. We heard from readers of previous editions that the book strikes a good balance between explaining the broader concepts supported with great hands-on examples, giving a light introduction to the mathematical underpinnings.
Why is it important to learn about GANs and reinforcement learning?
The first GANs paper had just come out two years before we started working on the second edition, but we weren't sure of its relevance. However, GANs have evolved into one of the hottest and most widely used deep learning techniques. People use them for creating artwork, colorizing and improving the quality of photos, and to recreate old video game textures in higher resolutions. It goes without saying that an introduction to GANs was long overdue.
Another important machine learning topic not included in previous editions is reinforcement learning, which has received a massive boost in attention recently. Thanks to impressive projects such as DeepMind's AlphaGo and AlphaGo Zero, reinforcement learning has received extensive news coverage. And just recently, it’s been used to compete with the world's top e-sports players in the real-time strategy video game StarCraft II. We hope that our new chapters can provide an accessible and practical introduction to this exciting field.
"Python Machine Learning 3rd edition is a very useful book for machine learning beginners all the way to fairly advanced readers, thoroughly covering the theory and practice of ML, with example datasets, Python code, and good pointers to the vast ML literature about advanced issues."--
Alex Martelli, Python Software Foundation Fellow, Co-author of Python Cookbook and Python in a Nutshell
"A brilliantly approachable introduction to machine learning with Python. Raschka and Mirjalili break difficult concepts down into language the layperson can easily understand while placing these examples within real-world contexts. A worthy addition to your machine learning library!"--
Dr Kirk Borne, Principal Data Scientist, Data Science Fellow, and Executive Advisor at Booz Allen Hamilton, and co-author of Ten Signs of Data Science Maturity
"Python Machine Learning, Third Edition is a highly practical, hands-on book that covers the field of machine learning, from theory to practice. I strongly recommend it to any practitioner who wishes to become an expert in machine learning. Excellent book!"--
Sebastian Thrun, CEO of Kitty Hawk Corporation, and chairman and co-founder of Udacity--This text refers to the paperback edition.
About the Author
Sebastian Raschka is an Assistant Professor of Statistics at the University of Wisconsin-Madison focusing on machine learning and deep learning research. Some of his recent research methods have been applied to solving problems in the field of biometrics for imparting privacy to face images. Other research focus areas include the development of methods related to model evaluation in machine learning, deep learning for ordinal targets, and applications of machine learning to computational biology.
Vahid Mirjalili obtained his Ph.D. in mechanical engineering working on novel methods for large-scale, computational simulations of molecular structures. Currently, he is focusing his research efforts on applications of machine learning in various computer vision projects at the Department of Computer Science and Engineering at Michigan State University. He recently joined 3M Company as a research scientist, where he uses his expertise and applies state-of-the-art machine learning and deep learning techniques to solve real-world problems in various applications to make life better.--This text refers to the paperback edition.
- Publication Date : December 12, 2019
- File Size : 24056 KB
- Print Length : 1079 pages
- Word Wise : Not Enabled
- Publisher : Packt Publishing; 3rd Edition (December 12, 2019)
- Language: : English
- ASIN : B07VBLX2W7
- Text-to-Speech : Enabled
- X-Ray : Not Enabled
- Enhanced Typesetting : Enabled
- Lending : Not Enabled
- Best Sellers Rank: #80,268 in Kindle Store (See Top 100 in Kindle Store)
- Customer Reviews:
Top reviews from the United States
There was a problem filtering reviews right now. Please try again later.
I returned the print copy and purchased the Kindle version, which is surprisingly good. Although I prefer a physical copy of reference books, in this case I would recommend the Kindle version.
As far as actual content, so far I am finding it well-written and informative.
1. Everything before chapter 13, before the book fully gets into deep learning and TensorFlow, are great. With already some background in python for data analysis (I have also taken the Andrew Ng's Coursera course on Machine Learning), this book supplements my knowledge greatly. The biggest highlight I would say is that it introduces you JUST ENOUGH concepts for you to understand how everything works. In addition, the contents are structured really well, too. If I were to rate this section of the book, I would give 10/10 although it would be better to have some exercises, you can always practice using Kaggle datasets.
2. Since chapter 13 when the book gets into deep learning, things get worse a little bit... The contents are still good in general, however the connections between contents might not be the case. The connections between contents are important for new learners because that helps them to understand how A leads to B and then leads to C. Here, I found the actual TensorFlow documentation a really good material to review along with the book. After reviewing those documentations, coming back to this book allows me to comprehend much more than reading the first time. In addition, if you are not careful enough, the deep learning sections also seems to have accuracy issues with its contents that could confuse people. Even though I have not finished the book, I would give 9/10 for everything I have read for deep learning.
I loved the 2nd edition as well as the care and effort the authors put into this book, but Packt's cheap printing ruins it for me. If I would have known, I would have just bought the kindle edition.
Update: I reached out to Packt publishing directly, and they told me Amazon prints these copies themselves. Amazon customer service refused to replace the copy I received since I'm passed the return window and missed it because I tried to reach out to Packt first. I suggest avoiding purchasing this book from Amazon and buying directly from Packt themselves. This has been a poor customer experience.
This is best of the books!
2. I placed the order on Jan 19 2020. When I open the last page of the book, I surprisingly saw "Made in the USA, 19 January 2020", which means they printed the book right after I placed the order.
3. I expect the billing is included with the book. I need it to request reimbursement from my company. But it is missing.
Today is Feb 11:
I got phone call saying that they provide replacement for free. The new book is on the road.
So I am happy to give a better overall rating.
Update: Was contacted by Amazon rep, and new book with corrected print was shipped free of charge. The replacement text looks great. The book itself is great.. well written, easy to follow, and contains a lot of good information.
Top reviews from other countries
Sorry for the rant, but I own countless programming books and in twenty years I've never experienced such a struggle with getting sample code running. In fairness, it could be a Python thing and nothing to do with the Author, but considerably more investigation should have been made into the building of a test environment for this book.
È un libro di livello intermedio molto improntato sulla pratica, per cui non mi sento di consigliarlo a chi non ha delle solide basi di python e delle buone nozioni sul machine learning.
Purtroppo, la qualità della stampa è davvero bassa. Il libro come si può intuire dal numero di pagine è davvero grosso (il font mi pare piuttosto grande). Inoltre, non capisco questa scelta da parte delle case editrici di stampare libri di questo tipo in bianco e nero.
Ein Mangel muss ich trotzdem nennen... Die Druckqualität sowie die Buchbindung sind nur "ausreichend". Das Buch liegt wie ein fetter Lappen in der Hand. Dennoch ist der Preis für ein 700+ Seiten langes buch unschlagbar!
Supongo que hacen impresión bajo demanda, y estas son las cosas que pasan.
NOTA: Como el contenido me interesa, lo he comprado en electrónico. Esta crítica es únicamente al libro en papel.