Discover one of the best Machine Learning books; simple, short, concise and elegant: The Hundred-Page Machine Learning book
About the book: 100 Pages of pure knowledge
The Hundred-Page Machine Learning Book is an excellent way for people with a scientific background to start learning about Machine Learning and Artificial Intelligence. People who are already familiar with the field will also enjoy it because of its short but to the point texts, clear visualisations, and well explained maths.
One of the reasons why we love reading so much is the following: some person (the author of a book) spends a lifetime learning, investigating, and collecting information about a certain topic. Then, he condenses that information for other people in a text document which can be no more than 100 pages sometimes. That is the case of this book. Years of experience in the Machine Learning and Artificial Intelligence world condensed into 100 beautifully written pages. A true gem.
Who is the Hundred Page Machine Learning book for?
As mentioned earlier, the 100 Machine Learning book can be equally enjoyed by those who already know about ML and those who are new to it.
If you are a courious person with some kind of STEM background that wants to discover what Machine Learning is all about, then this book is perfect for you.
If you are a person who works in the digital environment, and would like to get a better understanding of all of that Data Science stuff that they do somewhere in the company, then this book is also great for you too!
If you are a software engineer or a computer scientist that would like to start building Machine Learning applications, then this book could also be a very good starting point.
Lastly, if you are a Data Scientist or Machine Learning engineer and you want to have some fun, refresh some knowledge, and take a peak into the mind of a top AI researcher, then you will most definitely enjoy The Hundred page Machine Learning book.
Part I: Supervised Learning
Chapter 1 – Introduction: What Machine Learning is, supervised, unsupervised, and other kinds of learning techniques and how they work. The importance of Data.
Chapter 2 – Notation and Definitions: This chapter speaks about different data structures (matrices, arrays, sets…), defines the notation used through the book, and introduces different concepts that are fundamental to the mathematics of ML, like derivatives, gradients, and various statistical quantities and terms.
Chapter 3 – Fundamental Algorithms: Starting from the most simple linear regression, follows a path through Logistic Regression, Decision Trees, Support Vector Machines, and KNN. All with simple mathematical explanations and great visualisations.
Chapter 4 – Anatomy of a Learning algorithm: Chapter 4 describes gradient descent in depth with an example to illustrate how learning works. After this, the main way of implementing these models is described: using libraries like Scikit-Learn or Tensorflow instead of coding the algorithms from scratch by yourself.
Chapter 5 – Basic Practice: This chapter describes a full Data Science pipeline. Feature engineering, null-value imputation, feature scaling, and the main criteria for choosing one Machine Learning algorithm versus another. It explores train,test and validation sets, and describes what over-fitting and under-fitting are, describing regularisation techniques to avoid the former. To end, it speaks about model assessment using different metrics like the confusion matrix, accuracy or the ROC curve.
Chapter 6 – Neural Networks and Deep Learning: One of the hottest topics in Machine Learning: Deep Learning. This chapter describes the main elements of Artificial Neural Networks, starting from the Perceptron, and introduces the two most likely popular neural network architectures: Convolutional and Recurrent Neural Networks.
Chapter 7 – Problems and Solutions: this chapter is quite curious but provides great value. It speaks about specific Machine Learning problems and solutions like high dimensionality, multi-class classification, ensemble methods like bagging and boosting, attention models, and semi-supervised learning.
Chapter 8 – Advanced Practice: This chapter contains the description of specific techniques that are useful in some contexts, like transfer learning, handling imbalanced data sets. It also explores algorithm efficiency and why it is important.
Part II – Unsupervised Learning
Chapter 9 – Unsupervised Learning: This chapter explores unsupervised learning – what to do when our data doesn’t have labels. Different clustering techniques, and how to use them properly, as well as dimensionality reduction techniques like Principal Component Analysis and outlier detection.
Chapter 10 – Other Forms of Learning: This chapter is again, curious. It provides contents that most Machine Learning practitioners will have not heard much about, like Metric and Recommender Learning and introduces some more usual concepts like Word Embeddings
Chapter 11 – Conclusion: This chapter ends this fantastic book, briefly exploring concepts that have not been covered in the previous chapters like Topic Modelling GLM, or GANs and Reinforcement Learning.
If you want, check out the following video review: it covers what the book is about with a lovely slice of humour.
You can buy the book from Amazon at the best price here:
- Burkov, Andriy (Author)
- English (Publication Language)
- 160 Pages - 01/13/2019 (Publication Date) - Andriy Burkov (Publisher)
Summary of The Hundred Page Machine Learning book
If we had to sum up this book in one phrase, it would be something like the following:
“The best content per page Machine Learning book you can find”
In the 100 pages of the 100 page Machine Learning book, there is so much knowledge, and the explanations are so elegant and simple, that we would recommend grabbing this book to anybody who is willing to enter the amazing realm of Machine Learning, and carry it around for a while.
Even after reading it for a first time, it is a great tool to refresh your knowledge of various concepts. It is so beautifully explained that it is a real pleasure to read. The author has made a real outstanding effort to condense so much content into a book of this size, with very concise and pedagogical explanations.
We hope you enjoy them as much as we have.
Find other great Machine Learning books in our Machine Learning Books Section. Also here are other best-seller Machine Learning book from amazon:
- Use scikit-learn to track an example ML project end to end
- Explore several models, including support vector machines, decision trees, random forests, and ensemble methods
- Exploit unsupervised learning techniques such as dimensionality reduction, clustering, and anomaly detection
- Dive into neural net architectures, including convolutional nets, recurrent nets, generative adversarial networks, autoencoders, diffusion models, and transformers
- Use TensorFlow and Keras to build and train neural nets for computer vision, natural language processing, generative models, and deep reinforcement learning
Thanks for reading howtolearnmachinelearning!
Tags: The Hundred Page Machine Learning book, The 100 page Machine Learning Book, Best Books to Learn Machine Learning, Machine Learning books