# How Machines Learn to Ignore the Noise (Kevin Ellis + Zenna Tavares)

Page: https://stenobird.com/podcast/machine-learning-street-talk/how-machines-learn-to-ignore-the-noise-kevin-ellis-zenna-tavares
Text version: https://stenobird.com/podcast/machine-learning-street-talk/how-machines-learn-to-ignore-the-noise-kevin-ellis-zenna-tavares.md
Podcast: [Machine Learning Street Talk (MLST)](https://stenobird.com/podcast/machine-learning-street-talk)
Published: 2025-04-08T21:03:31+00:00
Episode link: https://podcasters.spotify.com/pod/show/machinelearningstreettalk/episodes/How-Machines-Learn-to-Ignore-the-Noise-Kevin-Ellis--Zenna-Tavares-e319n04
Audio file: https://anchor.fm/s/1e4a0eac/podcast/play/101030340/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2025-3-8%2Feca73139-5076-05da-1c71-0c4421ae52e9.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/machine-learning-street-talk/episodes/how-machines-learn-to-ignore-the-noise-kevin-ellis-zenna-tavares
Duration seconds: 4615

## Resource

Prof. Kevin Ellis and Dr. Zenna Tavares talk about making AI smarter, like humans. They want AI to learn from just a little bit of information by actively trying things out, not just by looking at tons of data. They discuss two main ways AI can "think": one way is like following specific rules or steps (like a computer program), and the other is more intuitive, like guessing based on patterns (like modern AI often does). They found combining both methods works well for solving complex puzzles like ARC. A key idea is "compositionality" - building big ideas from small ones, like LEGOs. This is powerful but can also be overwhelming. Another important idea is "abstraction" - understanding things simply, without getting lost in details, and knowing there are different levels of understanding. Ultimately, they believe the best AI will need to explore, experiment, and build models of the world, much like humans do when learning something new. SPONSOR MESSAGES: *** Tufa AI Labs is a brand new research lab in Zurich started by Benjamin Crouzier focussed on o-series style reasoning and AGI. They are hiring a Chief Engineer and ML engineers. Events in Zurich. Goto https://tufalabs.ai/ *** TRANSCRIPT: https://www.dropbox.com/scl/fi/3ngggvhb3tnemw879er5y/BASIS.pdf?rlkey=lr2zbj3317mex1q5l0c2rsk0h&dl=0 Zenna Tavares: http://www.zenna.org/ Kevin Ellis: https://www.cs.cornell.edu/~ellisk/ TOC: 1. Compositionality and Learning Foundations [00:00:00] 1.1 Compositional Search and Learning Challenges [00:03:55] 1.2 Bayesian Learning and World Models [00:12:05] 1.3 Programming Languages and Compositionality Trade-offs [00:15:35] 1.4 Inductive vs Transductive Approaches in AI Systems 2. Neural-Symbolic Program Synthesis [00:27:20] 2.1 Integration of LLMs wit…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/machine-learning-street-talk/episodes/how-machines-learn-to-ignore-the-noise-kevin-ellis-zenna-tavares/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/machine-learning-street-talk/how-machines-learn-to-ignore-the-noise-kevin-ellis-zenna-tavares.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.