Branson Mark J. Machine Learning with Python: A Step-By-Step Guide in Learning from Scratch. Machine Learning and Deep Learning with Python, a Practical Learning with Scikit-Learn and Tensor Flow with Examples

Independently published, 2019 — 217 p. — ISBN: 9781712506578.This book explicitly gives the reader layman’s introduction to machine learning with implementation in Python libraries particularly using Scikit learn and Tensor flow. We will learn about machine learning and its subset deep learning in detail along with program codes that will give a good overview for the developers. We will also discuss in detail about different machine learning algorithms like support vector machine, Linear regression method in detail with Python examples. In the second part of the book, we will deal with Neural networks and implement them using Tensor Flow. This book is easily understood and deals with complex concepts explained in a simple way such that beginners can understand it easily.
Here we describe the most important topics explained in the book in no particular order:
A brief introduction to machine learning with a small known history and terminology that is closely related to machine learning.
We will then give a brief project structure of machine learning that can be used to understand the process that goes on with a data science project.
Then the book describes in detail about regularization and how to fit a model into the data.
In the next chapter, we will deal with gradient descent and optimization with Python implementation.
We will then learn about feature engineering, data preprocessing methods, cross-validation, and hyperparameter tuning in detail with Python code implementation.
The last section of the first part deals with machine learning algorithms and their implementation in detail.
The second part starts with a brief introduction to Neural networks and Neurons
The next two chapters will help us understand the complexity and importance of Neural networks. We will also build a Neural network using Python in this chapter.
The last chapter deals with huge data sets like webpages. We will introduce page ranking algorithm and its simplicity.Introduction to machine learning
Learning Classification
Supervised learning Unsupervised learning
Machine learning project structure
Fitting a Model to Data
Cost function optimization
False Positives and False Positives Confusion Matrix
Accuracy paradox
Cumulative Accuracy Profile
Classification algorithm summary
Handling, Cleaning and Preparing Data
Import data set
Handling missing data
Classification Data
Feature Engineering and Feature
Cross-validation
Challenges in Machine Learning
Escaping the Curse of Dimensionality
Machine Learning Algorithms
Introduction to Neural Networks
Advanced Understanding of Neural Networks
Training Deep Neural Networks
Scaling Neural Networks for Huge Datasets