ML Resource — August 3

Prompt-based learning is a new paradigm in NLP that has been gaining prominence in the last year. Liu et al. have written a great and accessible survey paper on prompting methods and prompt-tuning strategies.

Christopher Potts has kindly shared his ACL 2021 keynote on Youtube, giving us great food-for-thought on what it means to build socially responsible NLP systems.

The DLRL Summer School was held last week. While I hope the videos of the summer school will be uploaded too, here are slides from one of the sessions on uncertainty in deep learning by Balaji Lakshminaryanan.

An open source implementation of OpenAI’s CLIP model is available now, courtesy Ilharco et al.

Aggregate Intellect

Aggregate Intellect is a Global Marketplace where ML Developers Connect, Collaborate, and Build. Connect with peers & experts at https://ai.science or Join our Slack Community.

• Check out the user generated Recipes that provide step by step, and bite sized guides on how to do various tasks
• Join our ML Product Challenges to build AI-based products for a chance to win cash prizes
• Connect with peers & experts through the ML Discussion Groups or Expert Office Hours