Other Sellers on Amazon
+ Free Shipping
+ Free Shipping
+ $3.99 shipping
Mastering Machine Learning Algorithms: Expert techniques for implementing popular machine learning algorithms, fine-tuning your models, and understanding how they work, 2nd Edition Paperback – January 31, 2020
|New from||Used from|
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.
Frequently bought together
What other items do customers buy after viewing this item?
About the Author
Giuseppe Bonaccorso is Head of Data Science in a large multinational company. He received his M.Sc.Eng. in Electronics in 2005 from University of Catania, Italy, and continued his studies at University of Rome Tor Vergata, and University of Essex, UK. His main interests include machine/deep learning, reinforcement learning, big data, and bio-inspired adaptive systems. He is author of several publications including Machine Learning Algorithms and Hands-On Unsupervised Learning with Python, published by Packt.
There was a problem filtering reviews right now. Please try again later.
Few ever think to build the appliance from scratch but rather by one already made to serve their needs progressively adopting it as an augmentation to everyday life. Even easier is when these items can be cataloged in one place, shopped, and put into use immediately (think Sears catalog of 1888). In its first catalog, Sears sold jewelry and watches. The directories grew in popularity, and with time different products were added and tested, even whole houses!
While algorithms are not a new thing, thanks to the father of algebra: Abdullah Muhammad bin Musa al-Khwarizmi, it should NOT be challenging to catalog them. This book one of the best, like it, does that facilitating faster solutioning to get to the point of solving problems using built appliances (machine intelligence: algorithms).
There is complex math notation that gets thrown around without any extra explanation, so expect to consult other resources to help understand some of the math and theory if you're not a math expert. It's also very theoretical, and more of an academic focus rather than practical applications. There is a lot of text (sometimes entire pages full of only text) explaining concepts. Overall a good resource, but I recommend using it more as an encyclopedia-style reference for ML theory and concepts rather than a way to learn how to implement different ML techniques in Python.
There is something here for everyone. All of the classic/early ML algorithms/techniques are fully explained, including optimizers, loss functions, etc. The more advanced topics are masterfully handled as well.
Not only do we get excellent mathematical exposition of the above, but the accompanying code and examples are clear, practical, and relevant.
Now, in good conscience, I could not recommend this book to a complete beginner to ML. I believe there are more accessible texts out there for someone just looking to implement the libraries without getting deep into the whys and hows. So it is more of an intermediate to advanced text, but it doesn't mean that it reads like an academic paper either. Those with some mathematical training will enjoy it more, but very accessible nonetheless. There are little errors here and there but nothing so egregious as to discredit the entire content.
All in all, this is an excellent text for reference, an advanced course in ML, or just to have on hand to show you mean business. It should cost a lot more!
This is an amazing book with a LOT of detail. If you have a solid ML background and a good handle on the mathematics used in ML, then this book is for you. If not, then this is still a good book, but maybe not the next one you should be reading. Either way, it should still be on your list to buy.
What I Like:
Every chapter ends with a Further Reading section, something I look for in any AI book to have the option of going deeper into one particular area. Each algorithm contains the math needed to gain a deep understanding, but doesn't always show you how to work through it; assumptions are made about your level of math, but it's also not using a lot of pages to hand hold you through every little detail.
What I Didn't Like:
This should be a volume of a series that goes over all ML algorithms. It's a great reference if you already have a good understanding of the field, and can be used as a learning tool by the dedicated student, but I would have liked to see this as a later volume where all of the algorithms are given the same treatment, cross referenced, and are laid out in detail. I think an opportunity was lost.
What I Would Like to See:
I would like to see this expanded. Yes, it's nearly 800 pages already, but there are many other algorithms out there, including variations to ones given. That could be explored in more detail, such as trade offs for each variation. I hope the author writes more, as I did enjoy the book.
Overall, I give this book a 4.4 out of 5. If the second edition, which hope they write, standardizes the algorithms a bit more (giving each the same sections) as well as expanding it, then I would bump this up higher.