Machine Learning comes with the basis of Artificial Intelligence which is needed in many companies nowadays too. As they want to solve their crunch by themselves and for that they need to learn and seize the data sets before.

We’re still not this much evolved where machines could take the actions by their own, as for that we still got a long way to go!

So, from where can we start learning about Machines?

Well, to start anything new, books can be our best guides.

Here is the list of some books that I found would be conducive-

I will mention books which are used as an introduction to understanding the basics and get acquainted with the subject to the ones where you’re just starting with Machine Learning:

**Contents**hide

## 1. Understanding Machine Learning: “From Theory to Algorithms”

By Shai Shalev-Shwartz and Shai Ben-David

This is aiming for the students who want to learn the basics of Machine Learning.

And getting homespun with algorithms too.

This contains the fastest growing area of computer science in a principle way applications of algorithmic paradigms.

It was published in 2014 by Cambridge University.

Abstract of the book:

Theoretical application with fundamental knowledge of practical ideas. Mathematical derivations are to be transformed into practical algorithms. Topics like convexity and stability with algorithmic paradigm contain stochastic gradient descent, neural networks, and structured output learning; and emerging theoretical concepts such as the PAC-Bayes approach and compression-based bounds.

Basically this book is designed for an undergraduate or fresher in a graduate course.

The people who aren’t expert in the field of computer science, mathematics, engineering and statistics can also get access with the subject. The best thing about this book is , it covers those topics too which aren’t mentioned in other books.

For example, topics ranging from, how to download free datasets to the tools and machine learning libraries that will be needed. Data scrubbing techniques

- Regression analysis
- Clustering
- Basics of Neural Networks
- Bias/Variance
- Decision Trees

## 2. Machine Learning for Hackers: Case Studies and Algorithms to Get You Started (1st Edition)

Authors: Drew Conway & John Myles

Hackers can be referred to a good programmer too, it’s not always stating something in a negative sense.

Data crunching is cool sometimes!

The best part about this book?

Well, it contains huge amount of case studies and experiences instead of those typical boring maths problem and presentations.

Classification, prediction, optimization, and recommendations are the basics/patterns that how chapters are written.

After reading this book you will be able to write

algorithms in the R programming language and analyze datasets.

## 3. Machine Learning: The New AI (The MIT Press Essential Knowledge Series)

Author: Ethem Alpaydin

You might never imagine that product recommendations, voice recognition and interestingly self-driving cars too contain applications of Machine Learning.

As it’s range has increased insanely so the ability to convert data or ideas into knowledge has also evolved.

Topics like :

- Machine learning algorithms for pattern recognition
- Artificial neural networks
- Reinforcement learning
- Data science
- Ethical and legal implications of Machine Learning for data privacy and security.

## 4. Programming Collective Intelligence: Building Smart Web 2.0 Applications (1st Edition)

For any Intermediate/Expert in Machine Learning

Author and Publisher – Toby Segaran and O’Reilly Media

Do you want to understand what is behind search rankings, online matchmaking, product recommendations and social bookmarking?

Well, this book would be helpful for you to identify it as it demonstrates applications for Web 2.0 mine the enormous amount of data that is created by approximately 3 Billion people on the Internet.

This book was written even before 2007 and mentions the use of Python which helps us understand what the writer tries to deliver.

This is the reason it works as a guide to understanding Machine Learning.

Either it calls to gather data from applications or creating programs for accessing data from websites or it can be inferred the gathered data, this book has it all.

The stated algorithms can be further improved by efficiency and effectiveness.

The collective knowledge and intelligence of programming help to know about user experience, marketing, personal tastes, and human behaviour in general.

The things (codes in this case) which are mentioned in this book are some codes which can be used anywhere by you, which includes your web site, blog, Wiki or some application specialized for you.

The topics covered are stated below :

- Search engine algorithms
- Bayesian filtering
- Collaborative filtering techniques
- Support vector machines
- Evolving intelligence for problem-solving
- Methods for detecting groups or patterns
- Ways to make predictions(Like we always do)
- Non-negative matrix factorization

## 5. Pattern Recognition and Machine Deep learning

- Authors – Ian Goodfellow
- Yoshua Bengio
- Aaron Courville
- And at last the editor
- (Francis Bach)

Like the name of this book suggests, it entirely gives the deep idea and helps to learn the total application taking place after this.

Great things need time so was with this book as it took more than two and a half years and came out finally in 2016.

This textbook includes mathematical and conceptual background.

It covers relevant concepts in linear algebra.

- Probability and information theory.
- Numerical computations.
- It also describes
- Deep feedforward networks
- Regularization
- Optimization algorithms
- Convolutional networks
- Sequence modelling.

Speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames are some applications which are surveyed and written well-versed in this book.

The theoretical topics which are covered so far are having linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods(Sounds Interesting)

## 6. The Hundred-Page Machine Learning Book

Author and Publisher – Andriy Burkov

It is next to impossible to actually explain or even learn(according to reader’s perspective) “Machine Learning” in mere 100 pages.

(Quite Interesting, right?)

That too not only restricted to anything specific but covering everything about the subject really worth to read at least once!

The range of topics also varies, including:

- Anatomy of a learning algorithm
- Fundamental algorithms
- Neural networks and deep learning
- Other forms of learning
- Supervised and unsupervised learning(Sounds decent)

## 7. Introduction to Machine Learning with Python: A Guide for Data Scientists

Author – Andreas C. Müller & Sarah Guido

Publisher – O’Reilly Media

This book could be the guide to start your journey of learning the Machine Learning.

You can build your own solutions by the practical knowledge provided by this book.

This book is designed in a way where it is already assumed that readers have an understanding of matplotlib and NumPy libraries already.

Using Python and Scikit-learn library you will have better understanding of many concepts.

Topics which are covered in the book are:

- Advanced methods for model evaluation and parameter tuning
- Pipelines for chaining models and encapsulating workflow
- Representation of processed data
- Applications, fundamental concepts of machine learning
- Machine learning algorithms
- Methods for working with text data
- The Elements of Statistical Learning: Data Mining, Inference, and Predictaveragi

## 8. The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Authors – Trevor Hastie, Robert Tibshirani, and Jerome Friedman

Publisher – Springer

It is assumed to have an understanding of linear algebra which emphasizes mathematical derivations and definitions.

Concepts will be difficult for the fresher’s.

Where An Introduction to Statistical Learning is an alternative book for this if you want to get acquainted because things are written in a beginner-friendly way.

Topics covered are:

- Random forests
- Ensemble learning
- High-dimensional problems
- Linear methods for classification and regression
- Neural network
- Supervised and unsupervised learning
- Model inference and averaging

Books like, Pattern Recognition and Machine Learning Written by Christopher M. Bishop is also considered helpful for the ones who want to dive deep in the ocean of Pattern Recognition and Machine Learning.

## Natural Language Processing with Python, Paradigm of Artificial Intelligence Programming

(By Peter Norvig) and Artificial Intelligence for Humans is some books which teach algorithms like dimensionality, metrics of distances, clustering, Calculation of errors occurred, hill climbing, Nelder Mead, and linear regression and what not!

The list of the books mentioned above are based on some personal strife or that must’ve been recommended by some people who are into Machine Learning field.

Here are some sources mentioned:

https://towardsdatascience.com/machine-learning-books-you-should-read-in-2020-344b44d9a11e

https://www.quora.com/What-are-the-top-10-best-books-on-machine-learning

https://www.tableau.com/learn/articles/books-about-machine-learning

https://machinelearningmastery.com/machine-learning-books/