{"podcast":{"title":"Towards Data Science","slug":"towards-data-science","podcast_index_feed_id":249150,"rss_url":"https://anchor.fm/s/36b4844/podcast/rss","website_url":"http://towardsdatascience.com/","image_url":"https://d3t3ozftmdmh3i.cloudfront.net/production/podcast_uploaded_nologo/473625/473625-1610835245953-54c8379418937.jpg","author":"The TDS team","episode_count":130,"summary":"Note: The TDS podcast's current run has ended. Researchers and business leaders at the forefront of the field unpack the most pressing questions around data science and AI.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/towards-data-science"},"episode":{"title":"106. Yang Gao - Sample-efficient AI","slug":"106-yang-gao-sample-efficient-ai","published_at":"2021-12-08T15:26:47+00:00","page_url":"https://stenobird.com/podcast/towards-data-science/106-yang-gao-sample-efficient-ai","show_page_url":"https://stenobird.com/podcast/towards-data-science","url":"https://podcasters.spotify.com/pod/show/towardsdatascience/episodes/106--Yang-Gao---Sample-efficient-AI-e1baruu","audio_url":"https://anchor.fm/s/36b4844/podcast/play/44445086/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2021-11-6%2F1b5c67a0-db93-7622-8ec3-a52fc4bd5392.m4a","summary":"Historically, AI systems have been slow learners. For example, a computer vision model often needs to see tens of thousands of hand-written digits before it can tell a 1 apart from a 3. Even game-playing AIs like DeepMind’s AlphaGo, or its more recent descendant MuZero, need far more experience than humans do to master a given game. So when someone develops an algorithm that can reach human-level performance at anything as fast as a human can, it’s a big deal. And that’s exactly why I asked Yang Gao to join me on this episode of the podcast. Yang is an AI researcher with affiliations at Berkeley and Tsinghua University, who recently co-authored a paper introducing EfficientZero: a reinforcement learning system that learned to play Atari games at the human-level after just two hours of in-game experience. It’s a tremendous breakthrough in sample-efficiency, and a major milestone in the development of more general and flexible AI systems. ---  Intro music : ➞ Artist: Ron Gelinas ➞ Track Title: Daybreak Chill Blend (original mix) ➞ Link to Track: https://youtu.be/d8Y2sKIgFWc --- Chapters:  - 0:00 Intro - 1:50 Yang’s background - 6:00 MuZero’s activity - 13:25 MuZero to EfficiantZero - 19:00 Sample efficiency comparison - 23:40 Leveraging algorithmic tweaks - 27:10 Importance of evolution to human brains and AI systems - 35:10 Human-level sample efficiency - 38:28 Existential risk from AI in China - 47:30 Evolution and language - 49:40 Wrap-up","meta_description":"Historically, AI systems have been slow learners. For example, a computer vision model often needs to see tens of thousands of hand-written digits before…","key_points":[],"chapters":[],"topics":[],"duration_seconds":2993,"processing_state":"failed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/towards-data-science/episodes/106-yang-gao-sample-efficient-ai/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/towards-data-science/106-yang-gao-sample-efficient-ai.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}