Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems
- Downloads：6705
- Type：Epub+TxT+PDF+Mobi
- Create Date：2022-10-27 06:52:31
- Update Date：2025-09-07
- Status：finish
- Author：Aurélien Géron
- ISBN：1098125975
- Environment：PC/Android/iPhone/iPad/Kindle
- Download
Summary
A series of Deep Learning breakthroughs have boosted the whole field of machine learning over the last decade。 Now that machine learning is thriving， 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 frameworks—Scikit-Learn and TensorFlow—author Aurélien Géron helps you gain an intuitive understanding of the concepts and tools for building intelligent systems。 You’ll learn how to use a range of techniques， starting with simple Linear Regression and progressing to Deep Neural Networks。 If you have some programming experience and you’re ready to code a machine learning project， this guide is for you。
This hands-on book shows you how to use:
Scikit-Learn， an accessible framework that implements many algorithms efficiently and serves as a great machine learning entry point
TensorFlow， a more complex library for distributed numerical computation， ideal for training and running very large neural networks
Practical code examples that you can apply without learning excessive machine learning theory or algorithm details
By using concrete examples， minimal theory， and two production-ready Python frameworks—Scikit-Learn and TensorFlow—author Aurélien Géron helps you gain an intuitive understanding of the concepts and tools for building intelligent systems。 You’ll learn how to use a range of techniques， starting with simple Linear Regression and progressing to Deep Neural Networks。 If you have some programming experience and you’re ready to code a machine learning project， this guide is for you。
This hands-on book shows you how to use:
Scikit-Learn， an accessible framework that implements many algorithms efficiently and serves as a great machine learning entry point
TensorFlow， a more complex library for distributed numerical computation， ideal for training and running very large neural networks
Practical code examples that you can apply without learning excessive machine learning theory or algorithm details
Reviews
Mateo Zapata López
，
Excelente libro el cual te lleva de la mano sobre el aprendizaje automático y el aprendizaje profundo。
Paul Larripa
，
This review has been hidden because it contains spoilers。 To view it， click here。 DataScience and ML plan:（0） Ace the Data Science Interview （Kevin Huo）（1） Business Data Science（2） Naked Statistics — Stripping the Dread From the Data（3） Machine Learning Simplified（4） Hands-On Machine Learning with Scikit-Learn， Keras & TensorFlow， 3rd Edition（5） Practical Statistics for Data Scientists（6） Elements of Statistical Learning（7） Machine Learning Yearning（8） Artificial Intelligence in Practice: How 50 Successful Companies Used AI （9） Deep Learning Illustrated（10） Deep Learning with DataScience and ML plan:（0） Ace the Data Science Interview （Kevin Huo）（1） Business Data Science（2） Naked Statistics — Stripping the Dread From the Data（3） Machine Learning Simplified（4） Hands-On Machine Learning with Scikit-Learn， Keras & TensorFlow， 3rd Edition（5） Practical Statistics for Data Scientists（6） Elements of Statistical Learning（7） Machine Learning Yearning（8） Artificial Intelligence in Practice: How 50 Successful Companies Used AI （9） Deep Learning Illustrated（10） Deep Learning with Python（11） Deep Learning （by Ian Goodfellow et al）（12） Interpretable Machine Learning with Python（13） Mastering 'Metrics: The Path from Cause to Effect 。。。more
Md。 Musfiqur Rahaman
，
One of the best book for learning and applying Machine Learning Fundamentals。 Anyone who is started learning Machine Learning should keep this book with him/her。
Okta "Oktushka" N。
，
Straightforward tutorial with prompt and concise theoretical explanation。
Shilpa Subrahmanyam
，
The best book I've read on machine learning fundamentals to-date。 I've started to recommend this book to everyone I mentor in the space。 The best book I've read on machine learning fundamentals to-date。 I've started to recommend this book to everyone I mentor in the space。 。。。more
Akrit Woranithiphong
，
Great book on Machine Learning。 If you know Python and wanted to learn Machine Learning without any guidance or place to start， this book is the way to go！
Dan Contreras
，
Esta cosa es la pinshi biblia de Inteligencia Artificial y el mejor recurso de entrada para cualquier principiante。 El libro es una obra de amor por parte de Aurelien Geron y se nota en cada página， cada ejercicio de código y cada gráfica。 El autor no empieza con el supuesto que ya traes un doctorado en Matemáticas y te va llevando de la manita a través de cada concepto complejo que va a introducir， con ejemplos perfectamente bien planteados。Si， tuve que ponerme a ver videos de Youtube para ente Esta cosa es la pinshi biblia de Inteligencia Artificial y el mejor recurso de entrada para cualquier principiante。 El libro es una obra de amor por parte de Aurelien Geron y se nota en cada página， cada ejercicio de código y cada gráfica。 El autor no empieza con el supuesto que ya traes un doctorado en Matemáticas y te va llevando de la manita a través de cada concepto complejo que va a introducir， con ejemplos perfectamente bien planteados。Si， tuve que ponerme a ver videos de Youtube para entender ciertos conceptos donde incluso Gerón se los pasa como si fueran nada， pero comparado con el resto de la literatura， sigue empezando por las piedritas。 Al final de 19 capitulos y más de 700 páginas， sales sabiendo más que cualquier maestria de medio pelo en Data Science。 Asi de completo está。 Fácil metes 3 materias de Machine Learning a nivel maestria en este libro。 Altamente recomendado si estás empezando en el tema。 Mi compañero constante desde Octubre。 。。。more
Sebastian
，
An excellent reference for anyone who wants to get an overview of existing Machine Learning algorithms and learn when and how to apply a suitable model to a given problem。 In my opinion， the author strikes a perfect balance between detail and practicality in this textbook， thus providing a pragmatic and easy-to-follow guide for anyone willing to learn。You do not need any prerequisites to read this book other than a working knowledge of the Python programming language and some rudimentary underst An excellent reference for anyone who wants to get an overview of existing Machine Learning algorithms and learn when and how to apply a suitable model to a given problem。 In my opinion， the author strikes a perfect balance between detail and practicality in this textbook， thus providing a pragmatic and easy-to-follow guide for anyone willing to learn。You do not need any prerequisites to read this book other than a working knowledge of the Python programming language and some rudimentary understanding of statistical data analysis concepts。 Along the way， you will learn the basics of scikit-learn， Tensorflow 2， and Keras and see all of these frameworks in action。It is also easy and straightforward to access the accompanying Jupyter notebooks from the author's GitHub repository and run them， e。g。， in Google's Colaboratory。 。。。more
Ritu Tiwari
，
One of the best ML book which covers the basics very clearly。Add on is hands on excercises。Must for people thinking to move in ML
bimri
，
Such a supreme text of ML/DL/RL。 Systematically and seamlessly flowing。 Which it shall remain a read for the ages: having shaped the paths of so many ML engineers' careers！ Each reread， something stands out and I get eager to start it all over again！ Such a supreme text of ML/DL/RL。 Systematically and seamlessly flowing。 Which it shall remain a read for the ages: having shaped the paths of so many ML engineers' careers！ Each reread， something stands out and I get eager to start it all over again！ 。。。more
Michael
，
Great book for getting to know the basics of data science in Python。 Pretty easy to find your way around for reference。 Recommended for people looking to break into data science from other parts of CS/sciences。
Max McKinnon
，
Fantastic book。 Lots of scrappy example code with authoritative and correct detailed information and opinionated advice。Before this book， i had never done NLP， and all the blog posts and github stuff online is good and all if I knew what i was looking for already， but I didn’t。 The project on tfidf and naive bayes， which is a bread and butter way to do a basic first pass at a language classification problem， helped so much get me off the ground in an intelligent way。 This project really took off Fantastic book。 Lots of scrappy example code with authoritative and correct detailed information and opinionated advice。Before this book， i had never done NLP， and all the blog posts and github stuff online is good and all if I knew what i was looking for already， but I didn’t。 The project on tfidf and naive bayes， which is a bread and butter way to do a basic first pass at a language classification problem， helped so much get me off the ground in an intelligent way。 This project really took off， deep learning methods replaced as the project scaled out， and it was the experience I needed to get a full time job in an NLP ML role at Google， something I never thought would ever happen。I referenced some other sections in this book too on a different project that had some lightweight sklearn models involved。 Overall， it’s a fantastic bridge with plenty of correct and prioritized opinion and advice to go from “i kind of know machine learning” to “i know how to read the sklearn docs and build what i need” 。。。more
Neil Mascarenhas
，
This one was old edition。 So it must be revised。 Very simple way to learn and implement machine learning models！
Rick Sam
，
A Good Introduction Book written for Beginners to give an overview of Machine Learning。 So， What do I require to understand？ 1。 Patience2。 Summarizing many times3。 Asking Questions 4。 Applying， Solving Problems Recommended for Data Scientists， Machine Learning， ResearchersDeus Vult， Gottfried
Pacific Lee
，
What more can be said about this excellent tome。 I used it in preparing for the TensorFlow Developer Certificate exam， and so mainly focused on the second half （chapters 10+）。 I would say if you are just looking to pass， the “DeepLearning。AI TensorFlow Developer Professional Certificate” on Coursera is more than enough。 This book can serve you as a supplemental， going deeper into the foundational deeplearning topics with practical exercises on GitHub。 It has been updated for TF2， and the pricing What more can be said about this excellent tome。 I used it in preparing for the TensorFlow Developer Certificate exam， and so mainly focused on the second half （chapters 10+）。 I would say if you are just looking to pass， the “DeepLearning。AI TensorFlow Developer Professional Certificate” on Coursera is more than enough。 This book can serve you as a supplemental， going deeper into the foundational deeplearning topics with practical exercises on GitHub。 It has been updated for TF2， and the pricing is more than reasonable。 Highly recommended 5/5。 。。。more
Stan Koko
，
Najlepiej napisana książka o machinę learningu w Pythonie jaką czytałem。
Andrew Breza
，
Hands on Machine Learning （HOML） is an excellent book for data scientists of all experience levels。 It covers a dizzying array of topics， meaning you're bound to find something you either don't already know or have long ago forgotten。 When you want to go deeper into a topic， the book offers citations to research papers and a collection of Jupyter notebooks。 Hands on Machine Learning （HOML） is an excellent book for data scientists of all experience levels。 It covers a dizzying array of topics， meaning you're bound to find something you either don't already know or have long ago forgotten。 When you want to go deeper into a topic， the book offers citations to research papers and a collection of Jupyter notebooks。 。。。more
Michel-Pierre Jansen
，
This book is a very welcome introduction to ML， I think its one of the most complete introductory books I have read so far。 The combination of a really useful github， practical implementation of ML projects and the core intuitions make the title truly accurate; Hands-on！ Originally I read the first part of the book to get a feeling with Scikit-learns ML tools for Python and recently I picked it up to read a few chapters on Deep Learning。 The book is clear in what it is and what it is not， and fo This book is a very welcome introduction to ML， I think its one of the most complete introductory books I have read so far。 The combination of a really useful github， practical implementation of ML projects and the core intuitions make the title truly accurate; Hands-on！ Originally I read the first part of the book to get a feeling with Scikit-learns ML tools for Python and recently I picked it up to read a few chapters on Deep Learning。 The book is clear in what it is and what it is not， and for what it aims to do， I can't find a better book。Read this book if you: are looking on how to implement machine learning and its core/best practices。 Need a good reference for some code and a good overview of some of the basic options to solve your problem using ML。Do not read this: If you need very deep understanding of how the algorithms work， I would refer to Elements for Statistical Learning as a good introductory book on the math/stats behind basic ML。 。。。more
Unemployed Techie
，
One of the best books on Machine Learning， and Deep Learning using TensorFlow 2。0。 This is a must-read book if you are planning to take the Google ML Certification。
Matthieu Miossec
，
It is impossible to absorb everything in this beast of a machine learning book on first reading （that will require revisiting several chapter and exercises）， but I certainly know a whole lot more than when I started reading it。 This does truly appear to be the best guide out there to truly get going。 Will definitely be revisiting soon。
Renan De Oliveira Pereira
，
What an amazing book， really。Lots of intuition behind the models， with clear and good explanations。The apex of this book， in my opinion， is the second chapter。 The author gives a good framework for approaching a machine learning project。 This stuff is gold， specially for people just entering the field like myself。Do yourself a favor: Head to your local library and buy this book。 Now。
Rohan
，
Author's github makes a valuable companion。 Author's github makes a valuable companion。 。。。more
Carlos
，
Great introduction to ML
Ezequiel Panzarasa
，
Excellent introduction to the subject！
Justin
，
For sure the definitive book for learning machine learning。 Gives you a just enough theory to be dangerous with the different ml algorithms。 The most valuable parts I found were the practical pieces of advice you won't find in a textbook， great metaphors for connecting very theoretical ideas to other experiences and great visualisations of concepts。 For sure the definitive book for learning machine learning。 Gives you a just enough theory to be dangerous with the different ml algorithms。 The most valuable parts I found were the practical pieces of advice you won't find in a textbook， great metaphors for connecting very theoretical ideas to other experiences and great visualisations of concepts。 。。。more
Priyavasanthan Pandiyan
，
ML is one way of implementing AI。 Instead of solving problems by code（limited to programmers bottleneck）， we train the system with data and try to find t similar pattern（solution）。 Two major problems addressed are regression and classification。 Scikit based examples were easy to follow and recreate。 Tensor and deep learning was not easy to follow。Linear regression， decision tree， gradient descent ， dimension reduction and random forest’s were well explained。In short， identify the algorithm， trai ML is one way of implementing AI。 Instead of solving problems by code（limited to programmers bottleneck）， we train the system with data and try to find t similar pattern（solution）。 Two major problems addressed are regression and classification。 Scikit based examples were easy to follow and recreate。 Tensor and deep learning was not easy to follow。Linear regression， decision tree， gradient descent ， dimension reduction and random forest’s were well explained。In short， identify the algorithm， train the model and solve。 Good book for hands on 👍。 。。。more
thoughtassault
，
A very good introduction to a broad range of Machine Learning concepts。 With a very solid practical approach to learning， many exercises and solutions; this book helped me tackle both the theoretical and practical aspects of ML。
John Doe
，
Seriously hands on。Basically step by step code presentation， just like reading official documentation but with explaining words。However， TensorFlow 2 already came out， parts of the code in the book are outdated even for TensorFlow 1。x。Be careful with the code， and remember to check official docs。
Annette Paul
，
Excellent book ！
Randy Hines
，