Mathematical Basics of AI for Precision Wellness, In: Harnessing AI and Machine Learning for Precision Wellness, Edited by Frederic Andres et al.

Document Type

Book

Publication Date

2025

Abstract

This chapter describes the basic mathematics of machine and deep learning and the extent to which it is needed to understand the basic concepts of machine and deep learning, hypothesis testing, and statistical evaluation of AI model results. In particular, the concepts of vectors, matrices, norms, and operations with them are explained, as well as the calculus for univariate and multivariate functions, derivatives, gradients, and integrals. The statistical part covers basic distributions, especially those needed for classification tasks, Bayes statistics and hypothesis testing. In the optimization part, the authors describe the concept of convexity, the gradient descent method and its challenges and possible improvements. The theoretical material is accompanied by simple examples and explanations, whereas in machine and deep learning these concepts are used.

Share

COinS