What do you think?
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.
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
Matching your tasks to the right machine-learning and deep-learning approachesVisualizing algorithms with TensorBoardUnderstanding and using neural networks
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
PART 1 - YOUR MACHINE-LEARNING RIGA machine-learning odysseyTensorFlow essentialsPART 2 - CORE LEARNING ALGORITHMSLinear regression and beyondA gentle introduction to classificationAutomatically clustering dataHidden Markov models PART 3 - THE NEURAL NETWORK PARADIGMA peek into autoencodersReinforcement learningConvolutional neural networksRecurrent neural networksSequence-to-sequence models for chatbotsUtility landscape
Machine Learning with TensorFlow gives readers a solid foundation in machine-learning concepts plus hands-on experience coding TensorFlow with Python.
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
Matching your tasks to the right machine-learning and deep-learning approachesVisualizing algorithms with TensorBoardUnderstanding and using neural networks
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
PART 1 - YOUR MACHINE-LEARNING RIGA machine-learning odysseyTensorFlow essentialsPART 2 - CORE LEARNING ALGORITHMSLinear regression and beyondA gentle introduction to classificationAutomatically clustering dataHidden Markov models PART 3 - THE NEURAL NETWORK PARADIGMA peek into autoencodersReinforcement learningConvolutional neural networksRecurrent neural networksSequence-to-sequence models for chatbotsUtility landscape
272 pages, Paperback
Published February 12, 2018
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