What do you think?
Rate this book
Machine Learning with TensorFlow
Summary
Machine Learning with TensorFlow gives readers a solid foundation in machine-learning concepts plus hands-on experience coding TensorFlow with Python.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the Technology
TensorFlow, Google's library for large-scale machine learning, simplifies often-complex computations by representing them as graphs and efficiently mapping parts of the graphs to machines in a cluster or to the processors of a single machine.
About the Book
Machine Learning with TensorFlow gives readers a solid foundation in machine-learning concepts plus hands-on experience coding TensorFlow with Python. You'll learn the basics by working with classic prediction, classification, and clustering algorithms. Then, you'll move on to the money exploration of deep-learning concepts like autoencoders, recurrent neural networks, and reinforcement learning. Digest this book and you will be ready to use TensorFlow for machine-learning and deep-learning applications of your own.
What's Inside
About the Reader
Written for developers experienced with Python and algebraic concepts like vectors and matrices.
About the Author
Author Nishant Shukla is a computer vision researcher focused on applying machine-learning techniques in robotics.
Senior technical editor, Kenneth Fricklas , is a seasoned developer, author, and machine-learning practitioner.
Table of Contents
Machine Learning with TensorFlow gives readers a solid foundation in machine-learning concepts plus hands-on experience coding TensorFlow with Python.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the Technology
TensorFlow, Google's library for large-scale machine learning, simplifies often-complex computations by representing them as graphs and efficiently mapping parts of the graphs to machines in a cluster or to the processors of a single machine.
About the Book
Machine Learning with TensorFlow gives readers a solid foundation in machine-learning concepts plus hands-on experience coding TensorFlow with Python. You'll learn the basics by working with classic prediction, classification, and clustering algorithms. Then, you'll move on to the money exploration of deep-learning concepts like autoencoders, recurrent neural networks, and reinforcement learning. Digest this book and you will be ready to use TensorFlow for machine-learning and deep-learning applications of your own.
What's Inside
About the Reader
Written for developers experienced with Python and algebraic concepts like vectors and matrices.
About the Author
Author Nishant Shukla is a computer vision researcher focused on applying machine-learning techniques in robotics.
Senior technical editor, Kenneth Fricklas , is a seasoned developer, author, and machine-learning practitioner.
Table of Contents
272 pages, Paperback
Published February 12, 2018
11 people are currently reading
95 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 6 of 6 reviews
October 23, 2019
Some context first:
I have some experienced with ML, I've had hands-on practice with supervised & unsupervised learning, even some basic NN, BUT using R & Octave, not Python. So my intention was to catch up on Python tool-set, especially TensorFlow & Jupyter to apply the previously acquired knowledge. It all made sense, because 2019 is the time of the so-called 2nd wave of ML - algorithms & basic methods are the well standardized & encapsulated in libraries & frameworks that if you know the applicability & basic idiomatic constructs, you don't even have to know all the math - you can treat it like a black-box.
But it didn't work with this book at all. It's actually quite good when describing the methods - where & when to use them, what are good examples of usage, etc. It also provides ready-to-use (?) examples in Python & TensorFlow. So what's the problem? Well, it fails in-between. It fails in presenting the foundation concepts of TF - what are its building blocks, how to use them (& how NOT to use them). What you get is an example, tagged with 5-7 comments & ... that's about it. Just go figure. Sure, I can do it, but isn't this a whole purpose? To build up the understanding of how does the example work so next time I can independently craft another, similar example?
In the end I was just irritated & I've read 85% of truly useful stuff on TF on-line docs - I don't feel the book was in any way substantial in my learning process.
I have some experienced with ML, I've had hands-on practice with supervised & unsupervised learning, even some basic NN, BUT using R & Octave, not Python. So my intention was to catch up on Python tool-set, especially TensorFlow & Jupyter to apply the previously acquired knowledge. It all made sense, because 2019 is the time of the so-called 2nd wave of ML - algorithms & basic methods are the well standardized & encapsulated in libraries & frameworks that if you know the applicability & basic idiomatic constructs, you don't even have to know all the math - you can treat it like a black-box.
But it didn't work with this book at all. It's actually quite good when describing the methods - where & when to use them, what are good examples of usage, etc. It also provides ready-to-use (?) examples in Python & TensorFlow. So what's the problem? Well, it fails in-between. It fails in presenting the foundation concepts of TF - what are its building blocks, how to use them (& how NOT to use them). What you get is an example, tagged with 5-7 comments & ... that's about it. Just go figure. Sure, I can do it, but isn't this a whole purpose? To build up the understanding of how does the example work so next time I can independently craft another, similar example?
In the end I was just irritated & I've read 85% of truly useful stuff on TF on-line docs - I don't feel the book was in any way substantial in my learning process.
July 21, 2019
There tends to be a lot of repetition between various machine learning books which essentially cover a lot of the same topics. This makes a lot of the content of most books skippable since you have seen it before. This is also true of this book where a lot of topics concerning the basics of machine learning are repeated and a lot of models described in more detail than necessary since you can find them described better in lecture notes or machine learning textbooks. The book also has a lot of repetition in the code samples like a lot of Manning titles. Good for what it is but perhaps quite a bit longer than it needs to be.
March 7, 2019
Prompts a brief explanation to Machine Learning with Tensorflow. Nishant describes Tensorflow as "the auto-focus" for machine learning. And his analogy is completely mind-shifting, because of the topics he introduces are the foundations of machine learning. I completely detoured from completing each exercise to just reading for intuition by the end of this book.
March 7, 2018
It's not exhaustive but a good start.
January 14, 2020
Good for Beginners
February 21, 2018
a decent reference book for solving various problems using tensorflow. However, having read this book, I do not feel I know tensorflow well enough to use it without external help and I neither feel more enlightened about machine learning. I think it was especially not impressive due to the fact I had just read "Deep learning with Python" just before, which is an outstanding book.
Displaying 1 - 6 of 6 reviews