This book has achieved the goal of explaining the conceptual simplicity underlying machine learning (ML) and deep learning, a subfield of ML, that uses multiple parameters to recognize complex patterns in pictures, sound and text. Machine learning is the study of computer algorithms that can improve automatically through experience and the use of data. It is seen as a part of artificial intelligence (AI).

Machine learning algorithms build a model based on sample data, known as “training data,” in order to make predictions or decisions without being explicitly programmed to do so. The author deems these algorithms and the underlying mathematics as elegant, a kind of ‘relatively simple math’ which one learns in high school like linear algebra and calculus plus the field of probability and statistics and the Gaussian distribution, also known as the normal distribution or bell curve, used as a foundational assumption for many algorithms and models.

We are living through a revolution in machine learning-powered AI that shows no signs of slowing down. This technology is based on relatively simple mathematical ideas, some of which go back centuries, like linear algebra and calculus. It took the birth and advancement of computer science and the kindling of 1990s computer chips designed for video games to ignite the explosion of AI that we see today.

Why Machines Learn : The Elegant Math Behind Modern AI. Anil Ananthaswamy. New York: Dutton (Penguin Random House), 2024.