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.
Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition Paperback – September 20, 2017
|New from||Used from|
Frequently bought together
Customers who bought this item also bought
Customers who viewed this item also viewed
From the Publisher
What's the key takeaway from your book?
That machine learning can be useful in almost every problem domain. I cover a lot of different subfields of machine learning in my book; by providing hands-on examples for each one of those topics, 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 broad audience of experienced programmers, as well as people who are new to programming. And by introducing the basic mathematics behind machine learning, we can appreciate machine learning being more than just black box algorithms, giving readers an intuition of the capabilities but also limitations of machine learning, and how to apply those algorithms wisely.
What’s new & updated in this second edition of Python Machine Learning?
Oh, where should I start. As time and the software world moved on after the first edition was released in September 2015, we decided to replace the introduction to deep learning via Theano. Don’t worry - we didn't remove it - but it got a substantial overhaul and is now based on TensorFlow, which has become a major player in my research toolbox since its release by Google in November 2015.
Along with the new introduction to deep learning using TensorFlow, the biggest additions to this new edition are three brand new chapters focusing on deep learning applications. In a similar vein to the rest of the book, these new chapters not only provide readers with practical instructions and examples, but also introduce the fundamental mathematics behind those concepts, which are an essential building block for understanding how deep learning works.
What makes this book stand out from other machine learning titles?
I certainly can't speak about all books on the market. However, since the first edition was released, I engaged in countless discussions with my readers, to help them with particular questions and to get their opinion on the parts they found unclear or topics they wish I had covered.
The connection between theory and praxis in particular was what readers found most helpful and somewhat lacking from other introductory texts (which, I heard, were either too theoretical or too practical). This constructive feedback has been invaluable for the second edition, helping me to focus on those parts that were still left unclear.
In a nutshell, the second edition of Python Machine Learning provides a healthy mix of theory and practical examples that most people found so helpful in the first edition, and the second edition adds on top of it with many refinements and additional topics based on the large corpus of invaluable reader feedback.
"I bought the first version of this book, and now also the second. The new version is very comprehensive. If you are using Python - it's almost a reference. I also like the emphasis on neural networks (and TensorFlow) - which (in my view) is where the Python community is heading.
I am also planning to use this book in my teaching at Oxford University. The data pre-processing sections are also good. I found the sequence flow slightly unusual - but for an expert level audience, it's not a major issue."--Ajit Jaokar, Data Science for IoT Course Creator and Lead Tutor at the University of Oxford / Principal Data Scientist
About the Author
Sebastian Raschka, author of the bestselling book, Python Machine Learning, has many years of experience with coding in Python, and he has given several seminars on the practical applications of data science, machine learning, and deep learning, including a machine learning tutorial at SciPy - the leading conference for scientific computing in Python.
While Sebastian's academic research projects are mainly centered around problem-solving in computational biology, he loves to write and talk about data science, machine learning, and Python in general, and he is motivated to help people develop data-driven solutions without necessarily requiring a machine learning background.
His work and contributions have recently been recognized by the departmental outstanding graduate student award 2016-2017, as well as the ACM Computing Reviews' Best of 2016 award. In his free time, Sebastian loves to contribute to open source projects, and the methods that he has implemented are now successfully used in machine learning competitions, such as Kaggle.
Vahid Mirjalili obtained his PhD 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.
Vahid picked Python as his number-one choice of programming language, and throughout his academic and research career he has gained tremendous experience with coding in Python. He taught Python programming to the engineering class at Michigan State University, which gave him a chance to help students understand different data structures and develop efficient code in Python.
While Vahid's broad research interests focus on deep learning and computer vision applications, he is especially interested in leveraging deep learning techniques to extend privacy in biometric data such as face images so that information is not revealed beyond what users intend to reveal. Furthermore, he also collaborates with a team of engineers working on self-driving cars, where he designs neural network models for the fusion of multispectral images for pedestrian detection.
If you buy a new print edition of this book (or purchased one in the past), you can buy the Kindle edition for only $2.99 (Save 85%). Print edition purchase must be sold by Amazon. Learn more.
For thousands of qualifying books, your past, present, and future print-edition purchases now lets you buy the Kindle edition for $2.99 or less. (Textbooks available for $9.99 or less.)
Top customer reviews
There was a problem filtering reviews right now. Please try again later.
This is the best book I've seen for professional software engineers to bootstrap themselves into Data Science, Machine Learning and (with the 2nd ed) Deep Learning. It makes heavy use of the scikit-learn library; and the latter chapters give an excellent high-level overview of TensorFlow. Books in this space can often feel either too basic or too academic. Not this one -- for me it hits the sweet spot of explaining and doing.
What I love about Raschka's writing is how he builds up from theory to practical code. It lays out the concepts, math, and code together which helps comprehension. So, if you happen to be rusty in math, like me, you can look to the code to help explain what the equations actually do. The chapters of the book build up from each other; so many of the examples feel like they can be used as recipes for building your own custom models.
Can't wait to attempt two RNN projects at the end of the book.
People who already have a decent level of skill and experience in statistics who want to:
- 1) Elevate their understanding of ML techniques without absolutely breaking their skull on dense theory
- 2) Learn how to implement the algorithms in Python and gain moderate proficiency in sci-kit learn
I would say it's not a beginner's book, but more for intermediates. I am half-way through and find it a little challenging, but definitely attainable. This balance I consider to be putting me right in the sweet spot for learning. To judge whether you're a good candidate for this book, you can compare your experience and skill to me :
I started this book after earning a PhD in the social sciences, which basically gave me good coverage in inferential and applied statistics (T, F distributions, p-values, confidence intervals, linear regression, one-way and factorial ANOVA, PCA, etc.). I also took a machine learning graduate course at my university and a few online courses in introductory ML for R. All of this background gave me solid grounding in statistics. With all this I still find this book somewhat challenging, but definitely not too hard. I'd say without my background I would find this book hard to get through. There is linear algebra, concepts like minimizing cost functions, bias/variance tradeoff, learning from errors, etc. So, if you are just starting out or reading the previous sentence and don't know what I'm talking about, I would recommend learning more stats fundamentals before starting this.
After you gain some proficiency in stats, come learn this book and elevate your understanding of the algorithms, add nuance to them, integrate them into your mental conceptual structures more fully (e.g. you'll know more nuances of ML, e.g. which subsets of algorithms are preferred for controlling more of the bias, variance, how random forest is basically bagging with a twist, how adaboost's treatment of classification errors has kind of an element of perceptron implementation, and many more).