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

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

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 Why Machines Learn: The Elegant Math Behind Modern AI. In this conversation we give a brief overview of some of the basic ideas, including the curse of dimensionality, backpropagation, transformer architectures, and more.

Blog post with transcript: https://www.preposterousuniverse.com/podcast/2025/11/24/336-anil-ananthaswamy-on-the-mathematics-of-neural-nets-and-ai/

Support Mindscape on Patreon.

Anil Ananthaswamy received a Masters degree in electrical engineering from the University of Washington, Seattle. He is currently a freelance science writer and feature editor for PNAS Front Matter. He was formerly the deputy news editor for New Scientist, a Knight Science Journalism Fellow at MIT, and journalist-in-residence at the Simon Institute for the Theory of Computing, University of California, Berkeley. He organizes an annual science journalism workshop at the National Centre for Biological Sciences at Bengaluru, India.


Jaksot(415)

291 | Venki Ramakrishnan on the Biology of Death and Aging

291 | Venki Ramakrishnan on the Biology of Death and Aging

Aging and death happen to the best of us, but there are increasing efforts to do something about it. That effort requires that we have some reasonable understanding of why aging happens, and what proc...

30 Syys 20241h 20min

290 | Hahrie Han on Making Multicultural Democracy Work

290 | Hahrie Han on Making Multicultural Democracy Work

It's a wonder democracy works at all -- a collection of people with potentially different interests have to agree to abide by majority vote even when it goes against their desires. But as we know, it ...

23 Syys 20241h 15min

289 | Cari Cesarotti on the Next Generation of Particle Experiments

289 | Cari Cesarotti on the Next Generation of Particle Experiments

As an experimental facility, the Large Hadron Collider at CERN in Geneva has been extraordinarily successful, discovering the Higgs boson and measuring multiple features of particle-physics interactio...

16 Syys 20241h 21min

288 | Max Richter on the Meaning of Classical Music Today

288 | Max Richter on the Meaning of Classical Music Today

It wasn't that long ago, historically speaking, that you might put on your tuxedo or floor-length evening gown to go out and hear a live opera or symphony. But today's world is faster, more technologi...

9 Syys 20241h 6min

AMA | September 2024

AMA | September 2024

Welcome to the September 2024 Ask Me Anything episode of Mindscape! These monthly excursions are funded by Patreon supporters (who are also the ones asking the questions). We take questions asked by P...

2 Syys 20243h 50min

287 | Jean-Paul Faguet on Institutions and the Legacy of History

287 | Jean-Paul Faguet on Institutions and the Legacy of History

One common feature of complex systems is sensitive dependence on initial conditions: a small change in how systems begin evolving can lead to large differences in their later behavior. In the social s...

26 Elo 20241h 32min

286 | Blaise Agüera y Arcas on the Emergence of Replication and Computation

286 | Blaise Agüera y Arcas on the Emergence of Replication and Computation

Understanding how life began on Earth involves questions of chemistry, geology, planetary science, physics, and more. But the question of how random processes lead to organized, self-replicating, info...

19 Elo 20241h 20min

285 | Nate Silver on Prediction, Risk, and Rationality

285 | Nate Silver on Prediction, Risk, and Rationality

Being rational necessarily involves engagement with probability. Given two possible courses of action, it can be rational to prefer the one that could possibly result in a worse outcome, if there's al...

12 Elo 20241h 11min

Suosittua kategoriassa Tiede

tiedekulma-podcast
rss-poliisin-mieli
rss-mita-tulisi-tietaa
docemilia
rss-duodecim-lehti
rss-luontopodi-samuel-glassar-tutkii-luonnon-ihmeita
utelias-mieli
radio-antro
rss-astetta-parempi-elama-podcast
rss-lapsuuden-rakentajat-podcast
rss-lihavuudesta-podcast
rss-sosiopodi