Ships in 1-5 business days: 2nd Edition of a Machine Learning Bestseller!
Learn insights based on the authors' experience and more specialized knowledge.

This book explains the theory, mathematical background, and practical Python coding for each machine learning concept.
It covers methods from early machine learning algorithms to neural networks (CNN/RNN).

Python libraries such as scikit-learn and TensorFlow are used.
This book is essential for a thorough understanding and practical application of machine learning.

The 2nd edition incorporates reader feedback from the 1st edition throughout and updates the libraries.
Chapters 13 onwards are almost entirely newly written.

● The original 1st edition was ranked in ACM's (Association for Computing Machinery)
"21st Annual list of Notable Books and Articles (2016)".
● The Japanese edition of the 1st edition was ranked in the Top 10 of the "IT Engineer Book Award 2017".

Chapter 1: Giving Computers the Ability to Learn from Data
Chapter 2: Classification - Training Simple Machine Learning Algorithms
Chapter 3: Classification - Utilizing the Machine Learning Library scikit-learn
Chapter 4: Data Preprocessing - Building Better Training Sets
Chapter 5: Compressing Data with Dimensionality Reduction
Chapter 6: Best Practices for Model Evaluation and Hyperparameter Tuning
Chapter 7: Ensemble Learning - Combining Different Models
Chapter 8: Machine Learning Applications 1 - Sentiment Analysis
Chapter 9: Machine Learning Applications 2 - Web Applications
Chapter 10: Regression Analysis - Predicting Continuous Target Variables
Chapter 11: Cluster Analysis - Analyzing Unlabeled Data
Chapter 12: Implementing Multilayer Artificial Neural Networks from Scratch
Chapter 13: Parallelizing Neural Network Training with TensorFlow
Chapter 14: TensorFlow Mechanisms and Features
Chapter 15: Image Classification - Deep Convolutional Neural Networks
Chapter 16: Modeling Sequential Data - Recurrent Neural Networks

◎ This is a translated edition of "Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition".

◎ A certain level of understanding of calculus/linear algebra, Python syntax, and data analysis libraries is required.

■ Excerpt from "Introduction"
Exploring and experimenting with practical sample code for machine learning is an excellent way to dive into this field, as it clarifies a wide range of concepts.
In this book, you will gain hands-on experience implementing machine learning using the Python language and machine learning libraries, and we will also introduce the mathematical concepts behind the algorithms. These concepts are essential for effectively utilizing machine learning. Therefore, this book is not just a practical guide.
We will explain machine learning concepts in detail as needed. We will intuitively explain how the algorithms work, how to use them, and, importantly, how to avoid the most common pitfalls.