Mathematical Analysis for Machine Learning and Data Mining

by Dan A Simovici

This compendium provides a self-contained introduction to mathematical analysis in the field of machine learning and data mining. The mathematical analysis component of the typical mathematical curriculum for computer science students omits these very important ideas and techniques which are indispensable for approaching specialized area of machine learning centered around optimization such as support vector machines, neural networks, various types of regression, feature selection, and clustering. The book is of special interest to researchers and graduate students who will benefit from these application areas discussed in the book.

968 pages, Hardcover

Published July 12, 2018

Reviews

[Carlos · Rating 2 out of 5]

I'm not sure if I should continue reading this book till the end. "Theorem" 4.7 is actually FALSE. It is not always true that subspaces of separable topological spaces are themselves separable (the Sorgenfrey plane is a standard counterexample). I wonder how many more false assertions this book has?