Why Machines Learn

The Elegant Math Behind Modern AI

De: Anil Ananthaswamy

Narrado por: Rene Ruiz

A rich, narrative explanation of the mathematics that has brought us machine learning and the ongoing explosion of artificial intelligence

Machine learning systems are making life-altering decisions for us: approving mortgage loans, determining whether a tumor is cancerous, or deciding whether someone gets bail. They now influence developments and discoveries in chemistry, biology, and physics—the study of genomes, extra-solar planets, even the intricacies of quantum systems. And all this before large language models such as ChatGPT came on the scene.

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, including linear algebra and calculus, the stuff of seventeenth and eighteenth-century mathematics. 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. In this enlightening book, Anil Ananthaswamy explains the fundamental math behind machine learning, while suggesting intriguing links between artificial and natural intelligence. Might the same math underpin them both?

As Ananthaswamy resonantly concludes, to make safe and effective use of artificial intelligence, we need to understand its profound capabilities and limitations, the clues to which lie in the math that makes machine learning possible.

*This audiobook contains a PDF of equations, graphs, and illustrations.

PLEASE NOTE: When you purchase this title, the accompanying PDF will be available in your Audible Library along with the audio.

©2024 Anil Ananthaswamy (P)2024 Penguin Audio

Reseñas de la Crítica

“An inspiring introduction to the mathematics of AI.”—Arthur I. Miller, author of The Artist in the Machine: The World of AI-Powered Creativity

“Some books about the development of neural networks describe the underlying mathematics while others describe the social history. This book presents the mathematics in the context of the social history. It is a masterpiece. The author is very good at explaining the mathematics in a way that makes it available to people with only a rudimentary knowledge of the field, but he is also a very good writer who brings the social history to life.”—Geoffrey Hinton, deep learning pioneer, Turing Award winner, former VP at Google, and Professor Emeritus at University of Toronto

“After just a few minutes of reading Why Machines Learn, you’ll feel your own synaptic weights getting updated. By the end you will have achieved your own version of deep learning—with deep pleasure and insight along the way.”—Steven Strogatz, New York Times bestselling author of Infinite Powers and professor of mathematics at Cornell University

Great history, hard to digest via audiobook

A lot of cool moments in the past century have led to AI’s current state, and this book does a great job capturing those moments with a glimpse into the math behind the breakthroughs. However, if you’ve taken ML/AI courses, you have already encountered a majority of the content in a more applied manner than the high-level proofs included here. An interesting read undoubtedly, but not the groundbreaking guide you might be looking for to understand & reverse-engineer why machines learn for your own career.

A great listen, but a physical book is pre appropriate

I enjoyed all the technical details and history. When the times came to look at a pdf, I wish I also had the physical copy.

Great book

Very in-depth. Following the pdf is a must if you want to understand the math, but not if you want the general ideas and the stories behind them.

Great listen, but keep the PDF handy.

There is a lot of math, so pay attention. I found I needed to reference the PDF throughout the book if I really wanted to understand what the chapter was trying to say.

Superb Introduction to a complex subject

It is clear the author knows his subject and wants to make it accessible to the education layman. The narrator has a pleasant voice and makes listening easy, but this is very much a work that is best accessed with the accompanying PDF open while listening to the narrator. There is much dense information and between the audio book and PDF I have learned so much I did not know, despite working with various AI projects as an enterprise architect the past several years. I highly recommend it to anyone motivated to learn more about machine learning, but this book is not for the casual reader.

Totally inappropriate for audio

This is a technical book with many equations and graphs. It should never have been converted to audio. It may very well be a fine book to read but it is not suited for listening unless you want to sit in front of a computer and look at the associated pdf file while listening - not for me. Wish I could return.

Buy a physical copy

This is one of the worst-sounding audiobooks I’ve ever heard—truly unlistenable. Even if the audio were tolerable, you’d still want the physical book for its heavy use of math and charts.

Lack of understanding

Not very clear as a beginner! What is the importance to each sequence. Why would I want to know the importance!

F your supplementary pdf

150 page supplementary pdf that is constantly referenced throughout the book, full of equations and technical pictures. Why make this into an audiobook at all if you need to study the text to understand the book?