Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems
by: Aurélien Géron (0)
Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data. This practical book shows you how.
By using concrete examples, minimal theory, and two production-ready Python frameworksâScikit-Learn and Tensor Flowâauthor AurĂ©lien GĂ©ron helps you gain an intuitive understanding of the concepts and tools for building intelligent systems. Youâll learn a range of techniques, starting with simple linear regression and progressing to deep neural networks. With exercises in each chapter to help you apply what youâve learned, all you need is programming experience to get started.
- Explore the machine learning landscape, particularly neural nets
- Use Scikit-Learn to track an example machine-learning project end-to-end
- Explore several training models, including support vector machines, decision trees, random forests, and ensemble methods
- Use the Tensor Flow library to build and train neural nets
- Dive into neural net architectures, including convolutional nets, recurrent nets, and deep reinforcement learning
- Learn techniques for training and scaling deep neural nets.
The Quotes
Applying ML techniques to dig into large amounts of data can help discover patterns that were not immediately apparent. This is called data mining.
Constraining a model to make it simpler and reduce the risk of overfitting is called regularization.
Machine Learning is the science (and art) of programming computers so they can learn from data.
The Reviews
This book gives you a hands-on approach to learning by doing. As opposed to the trendy deep learning books that dive deep into the weeds from the start, this book starts with the more traditional ML approaches (the Scikit-learn part) giving you a great deal of context and practical tools for solving all kinds of problems. Only after does he transition into deep learning concepts, giving you both a great overview and the background to understand when and where to apply the various techniques. Its code-focused so you'll have the option to run working code on real problems throughout the book.Most important for me, he focuses on explanation over hand-wavy equations that are rampant in other ML books. I say hand-wavy because they typically go like so: "Here's a hard concept. Rather than explain it well, I'll give you some linear algebra and calculus equations, remind you that this is stuff you should have learned in high school, and then move on." Authors probably feel justified in doing this, but after reading a book like this you understand what they are really doing: Skipping the hard-part of breaking difficult concepts down into chunks that can be consumed by a competent programmer, who is perhaps not an expert in "high school" math. Moreover, this author does so without dumbing down the content. That's the mark of someone who well understands both the content and the audience.This book is long and dense, and serves as both a guide and a reference. It is not a quick read / overview or light reading type book.
I've read all of the predominant machine learning related python books and this one is by far the best one. I was excited to see the second edition of this book come out. It is packed with new information (1.5x the length of the first edition) and updated for TensorFlow 2. I have the Kindle edition and find it very helpful to highlight key points. I look forward to receiving the print edition as well once it is released.EDIT: Just received the print edition of the book and it's in color! The first edition wasn't. This is a pleasant surprise as it makes it easier to read with various charts and graphics.
While I enjoy learning from this book, the math font in kindle edition is a mess which makes the reading unpleasant. I know to some this probably shouldn't be a deal breaker but for someone who wants to move from hard copy to kindle, it was a disappointment.
This is an update for my previous review.Recently, I gave one star for the poor ebook experience but with author's comment I realized the publisher updated the ebook and now everything is great in the ebook.As the name suggests, the book gives you a really hands-on experience on machine learning. This covers most of the recent main advancements in the field.
I'm very pleased with this book. I enjoy the little bits of humor here and there, and it does a great job not glossing over important details that might be a stumbling block for someone. I'm quite comfortable with python however I appreciated that he did go into depth on setting up virtual environments and best practices. I remember years back when I was starting that whole concept tripped me up so much, having this explained so well is going to save someone a lot of time. Also his code seems so far to be written in a very thoughtful way and has them all on github. He also goes into lots of gotchas and tips and tricks that just overall seem to add a certain maturity to his writing. He has obviously very well versed in machine learning.Overall I would recommend. It's been much more interesting than I expected.
Aurelien did it again!Whether you are a data scientist looking to start building predictive models in Python, or a software developer looking to become an ML engineer, look no further!The excellent balance between theory/background and implementation that was present in the first edition is kept, with the essential material additions made (e.g. the unsupervised learning in the "classical ML" part, or the Keras API, which is quickly becoming the most popular way to use TensorFlow).Needless to say, the Jupyter notes accompanying each chapter are more than helpful.Also, as a cherry on top, the illustrations in the printed version are now in color, which makes it even easier to read.In summary, this book is an absolute must-have for a Python-rooted data scientist / ML engineer!
I'm finishing up an MCS in Data Science from UIUC and I can tell you bar none that this book should be required reading in this subject. The required ML course at school was so confusing and they assumed WAY too much. Reading over the same topics in this book was like night and day in terms of explaining things in a way that makes sense. The images, graphs, and tables are clear and help a lot by providing visuals to the text explanation. I did notice a few typos but so far nothing critical. This is not a light read as it comes in at almost 800 pages but taking it model-by-model is easy to do.
The book was worth the wait! The publication quality of the print edition is great. Love the color illustrations. The one thing that I miss is that having bought the print edition, it would be sweet to have an offer to acquire the electronic edition at a reduced price but since Amazon now seems to be handling O'Reilly book sales and probably wants to sell as many Kindle editions as possible, a PDF copy of Hands-On Machine Learning, 2nd Ed., does not seem to be in my future at a bargain price. My review is preliminary - I've read bits of the online draft version-and the clarity and superb organization of GĂ©ron's writing convinced me that I wanted a finished copy of the book. My current avocational interest is Reinforcement Learning and GĂ©ron gives an excellent overview - to dive deep, one would probably still want to refer to Sutton & Barto's 2nd Ed. book (available on Amazon or for free online) or David Silver's excellent 2015 UCL lectures, also available online.. I will slowly work my way through GĂ©ron's book in its entirety but my primary reason for owning the book is as a reference. It makes a great roadmap to the current state of machine learning and, best of all, it makes learning about ML fun!
The Tokyo Olympics of 2020 got postponed to 2021. If there were a contest for best AI/ML book at the Olympics this year this book would have earned the gold medal ! I loved it so much that I read it at least twice, and each time I underlined/highlighted/took-notes. I love how lucidly the author explains concepts. He does an excellent job of explaining topics such as the model, the learning algorithm (also called the optimization algorithm), regularization hyperparameter, generalization etc. The examples are great and even if one does not know python programming it is easy to follow along. (I learned python a few months later, which made it even easier and more interesting to follow the examples in this and other books). While no one single book can teach one ML/AI, this book would make the Mount Rushmore of AI/ML books (along with (1) Intro to Statistical Learning by Hastie etc (2) Intro to Machine Learning by Alpaydin (3) Deep Learning by Goodfellow, Bengio etc). I highly recommend this book to anyone aspiring to get into the field of ML/AI.
The book begins with a short general discussion of machine learning, including data preparation, visualization, splitting into train and test sets, model fitting, and evaluation.The bulk of the book focuses on the techniques that are the current state-of-the-art -- ensembles and particularly deep learning. There is enough math to be convincing, but not so much to distract from practical applications. The sections describing deep learning architectures are particularly well done.Throughout the book, clear illustrations and fully disclosed Python 3 code enable the reader to replicate the author's work.
My company was awarded an NSF grant which required me to VERY quickly brush up on machine learning. and man, did this book do a good job. I'm comfortable with many ML concepts, and have applied them to real world applications to great effect. This is a comprehensive and detailed guide.As a software engineer with 8 or so years of experience, I have to say the code snippet quality is as clean as it gets as well. The author nailed every aspect.Sometimes I don't really get a section until I'm reading it for the third time.. but that's just how understanding goes for me. Wish I had an equivalent book for different areas of study.
