EPISODE · Jul 11, 2022 · 1H 13M
Multi-modal and Multi-task Models (S03 E04)
from The Technium · host The Technium
Multimodal and multitask models are machine learning models that can generalize. Multimodal models can generalize to understand different types of input, for example images and text. Multitask models can generalize their knowledge by applying what they’ve learned about one task to solve another task. Links/Resources: • MUM: https://blog.google/products/search/introducing-mum/ • Gato: https://www.youtube.com/watch?v=wSQJZHfAg18 • MIA: https://www.youtube.com/watch?v=L9kA8nSJdYw • Flamingo: https://www.deepmind.com/blog/tackling-multiple-tasks-with-a-single-visual-language-model • Flamingo explaining a funny photo: https://twitter.com/MelMitchell1/status/1522642194741538817 • Is LaMDA Sentient?: https://cajundiscordian.medium.com/is-lamda-sentient-an-interview-ea64d916d917 Chapters: 0:00 Intros 2:33 Multimodal and Multitasks Models 6:50 Deepmind's Gato: The All-Rounder Athlete 14:43 Google's MUM: The Search Assistant 18:12 Deepmind's Multimodal Interactive Agent: The Domestic Helper 22:31 Deepmind's Flamingo: Reasoning about Pictures 26:45 Why are these mind-blowing? 31:20 Machine Learning has come a looooong way 35:21 Could Flamingo be the real JARVIS? 38:56 Could MIA assist the elderly? 43:05 Multimodal AI for self driving cars 51:15 Multitask = A Shared Brain That Learns Everything 1:00:19 Could these models transcend human knowledge? 1:08:50 Breaking news: AI models are sentient 1:10:37 Is this just a local maximum or a path to AGI? 1:11:50 Outros ===== About “The Technium” ===== The Technium is a weekly podcast discussing the edge of technology and what we can build with it. Each week, Sri and Wil introduce a big idea in the future of computing and extrapolate the effect it will have on the world. Follow us for new videos every week on web3, cryptocurrency, programming languages, machine learning, artificial intelligence, and more! ===== Socials ===== WEBSITE: https://technium.transistor.fm/ SPOTIFY: https://open.spotify.com/show/1ljTFMgTeRQJ69KRWAkBy7 APPLE PODCASTS: https://podcasts.apple.com/us/podcast/the-technium/id1608747545
Embed this episode
What this episode covers
Multimodal and multitask models are machine learning models that can generalize. Multimodal models can generalize to understand different types of input, for example images and text. Multitask models can generalize their knowledge by applying what they’ve learned about one task to solve another task.
Ready to play
Multi-modal and Multi-task Models (S03 E04)
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.