Why Machines Learn: The Math Behind AI

In this episode Autumn and Anil Ananthaswamy discuss the inspiration behind his book "Why Machines Learn" and the importance of understanding the math behind machine learning. He explains that the book aims to convey the beauty and essential concepts of machine learning through storytelling, history, sociology, and mathematics. Anil emphasizes the need for society to become gatekeepers of AI by understanding the mathematical basis of machine learning. He also explores the history of machine learning, including the development of neural networks, support vector machines, and kernel methods. Anil highlights the significance of the backpropagation algorithm and the universal approximation theorem in the resurgence of neural networks. Keywords: machine learning, math, inspiration, storytelling, history, sociology, gatekeepers, neural networks, support vector machines, kernel methods, backpropagation algorithm, universal approximation theorem, AI, ML, physics, mathematics, science You can find Anil Ananthaswamy on Twitter @anilananth [https://x.com/anilananth] and his new book "Why Machines Learn [https://amzn.to/3zKiPSv]" Subscribe to Breaking Math wherever you get your podcasts. Become a patron of Breaking Math [https://www.patreon.com/breakingmath] for as little as a buck a month Follow Breaking Math on Twitter [https://x.com/breakingmathpod], Instagram [https://www.instagram.com/breakingmathmedia/], LinkedIn [https://www.linkedin.com/company/breaking-math/], Website [https://breakingmath.io/], YouTube [https://www.youtube.com/@BreakingMathPod], TikTok [https://www.tiktok.com/@breakingmathmedia] Follow Autumn on Twitter [https://x.com/1autumn_leaf] and Instagram [https://www.instagram.com/1autumnleaf/] Follow Gabe on Twitter [https://x.com/TechPodGabe]. Become a guest here [https://www.breakingmath.io/contact] email: breakingmathpodcast@gmail.com

Om Podcasten

Breaking Math is a deep-dive science, technology, engineering, AI, and mathematics podcast that explores the world through the lens of logic, patterns, and critical thinking. Hosted by Autumn Phaneuf, an expert in industrial engineering, operations research and applied mathematics, and Gabriel Hesch, an electrical engineer (host from 2016-2024) with a passion for mathematical clarity, the show is dedicated to uncovering the mathematical structures behind science, engineering, technology, and the systems that shape our future. What began as a conversation about math as a pure and elegant discipline has evolved into a platform for bold, interdisciplinary dialogue. Each episode of Breaking Math takes listeners on an intellectual journey—whether it’s into the strange beauty of chaos theory, the ethical dilemmas of AI, the deep structures of biological evolution, or the thermodynamics of black holes. Along the way, Autumn and Gabriel interview leading thinkers and working scientists from across the spectrum: computer scientists, quantum physicists, chemists, philosophers, neuroscientists, and more. But this isn’t just a podcast about equations—it’s a show about how mathematics influences the way we think, create, build, and understand. Breaking Math pushes back against the idea that STEM belongs behind a paywall or an academic podium. It’s for the curious, the critical, the creative—for anyone who believes that ideas should be rigorous, accessible, and infused with wonder. If you've ever wondered: * What’s the math behind machine learning? * How do we quantify uncertainty in climate models? * Can consciousness be described in AI? * Why does beauty matter in an equation? Then you’re in the right place. At its heart, Breaking Math is about building bridges—between disciplines, between experts and the public, and between the abstract world of mathematics and the messy, magnificent reality we live in. With humor, clarity, and deep respect for complexity, Autumn and Gabriel invite you to rethink what math can be—and how it can help us shape a better future. Listen wherever you get your podcasts. Website: https://breakingmath.io [https://breakingmath.io/] Linktree: https://linktr.ee/breakingmathmedia Email: breakingmathpodcast@gmail.com