336 | Anil Ananthaswamy on the Mathematics of Neural Nets and AI

<p>Machine learning using neural networks has led to a remarkable leap forward in artificial intelligence, and the technological and social ramifications have been discussed at great length. To understand the origin and nature of this progress, it is useful to dig at least a little bit into the mathematical and algorithmic structures underlying these techniques. Anil Ananthaswamy takes up this challenge in his book&nbsp;<a href="https://anilananthaswamy.com/why-machines-learn" rel="noopener noreferrer" target="_blank"><em>Why Machines Learn: The Elegant Math Behind Modern AI</em></a>. In this conversation we give a brief overview of some of the basic ideas, including the curse of dimensionality, backpropagation, transformer architectures, and more.</p><p>Blog post with transcript: <a href="https://www.preposterousuniverse.com/podcast/2025/11/24/336-anil-ananthaswamy-on-the-mathematics-of-neural-nets-and-ai/" rel="noopener noreferrer" target="_blank">https://www.preposterousuniverse.com...