Zero-shot multitask learning (Practical AI #158)

In this Fully-Connected episode, Daniel and Chris ponder whether in-person AI conferences are on the verge of making a post-pandemic comeback. Then on to BigScience from Hugging Face, a year-long research workshop on large multilingual models and datasets. Specifically they dive into the T0, a series of natural language processing (NLP) AI models specifically trained for researching zero-shot multitask learning. Daniel provides a brief tour of the possible with the T0 family. They finish up with a couple of new learning resources.

Join the discussion

Changelog++ members save 5 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• RudderStack – Smart customer data pipeline made for developers. RudderStack is the smart customer data pipeline. Connect your whole customer data stack. Warehouse-first, open source Segment alternative.
• iMerit ML DataOps Summit – A FREE virtual event on December 2nd, 2021! iMerit is excited to gather 1000+ senior leaders at the forefront of deploying data solutions that power machine learning and artificial intelligence. Learn more and register to attend at imerit.net/dataops
• Fastly – Compute@Edge free for 3 months — plus up to $100k a month in credit for an additional 6 months. Fastly’s Edge cloud network and modern approach to serverless computing allows you to deploy and run complex logic at the edge with unparalleled security and blazing fast computational speed. Head to fastly.com/podcast to take advantage of this limited time promotion!

Featuring:

• Chris Benson – Website, GitHub, LinkedIn, Bluesky, X
• Daniel Whitenack – Website, GitHub, X

Show Notes:

• InfoQ: BigScience Research Workshop Releases AI Language Model T0
• Hugging Face: bigscience / T0pp
• Multitask Prompted Training Enables Zero-Shot Task Generalization
• IEEE Specturm: How Deep Learning Works
• 5 Deep Learning Activation Functions You Need to Know

Something missing or broken? PRs welcome!