Machine Learning for Hackers  (English, Paperback, Conway Drew)

Machine Learning For Hackers comprehensively covers different aspect of the subject, including classification, optimization, prediction, prevention, and more.

Summary Of The Book

Machine Learning For Hackers, published in 2012, teaches readers how to work with, explore and manipulate data, and how to make use of different machine learning techniques and statistics tools.

Machine Learning For Hackers contains twelve chapters, the first of which is Using R. Readers are then introduced to data exploration, a section which explains standard deviations and variances, the meaning of data, and how one can infer the types of columns in a given data.

The authors teach readers how to filter spam by using the the Bayesian Classifier. This methodology allows the computer to detect a spam email by only analyzing the text. Furthermore, readers can also learn how to order emails by priority. Those who are keen to know how to predict web traffic and understand correlations, will find Machine Learning For Hackers to be a very useful guide.

Topics like preventing overfitting, building a market index, and breaking codes are also included. Machine Learning For Hackers elucidates on how to analyze social graphs, and hack into Twitter in order to build whom-to-follow recommendations.

This guide has been designed to ensure that it doesn’t seem like a typical math-heavy textbook. Each topic in this book starts off with a problem, the tools to solve it, and sometimes case studies. Readers will learn how to write simple algorithm, and how to analyze sample data sets. Machine Learning for Hackers can be used by programmers with a background in academics, government, business, amongst others.

About The Authors

Drew Conway is an author, and former computational social scientist in the counter-terrorism unit of the U.S. intelligence community.
He has co-authored Machine Learning for Email.

Conway is doing his Ph.D in Politics from the New York University (NYU). He is studying international conflicts, relations, and terrorism using tool of statistics, computer science, and maths. His expertise lies in the application of computational methods to social and behavioral problems at large-scale. He has been a consultant to many Fortune 100 companies, government agencies, and academic institutions. Conway lives in New York.

John Myles White is an author, student, and Statistics and Machine Learning educator.

He has written Bandit Algorithms for Website Optimization.

At present, White is a Ph.D scholar at the Princeton Psychology Department. The author is an active participant in the data science movement, and his interests like in Statistics, Machine Learning, and R. He maintains popular R packages like log4r, and ProjectTemplate. White lives in Princeton, New Jersey.