Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

Summary

Join us for a practical exploration of Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction, a fresh look on meta continual learning by Yichen Wu et al. (2024).

Requirements

• Join the AI Maker Community Slack Workspace: The communication during the session will happen through our Slack Workspace, in the #ai-maker-sessions channel: https://join.aimaker.community

• Participants will need to have a Kaggle account, as this will be a practical exploration using Kaggle Notebooks. Make sure to verify your account, so that you can access the GPUs on the platform.

• Please register for this free event on Eventbrite.

Event Details

This is an online event. We will post a link to the session in Slack shortly before the session starts.

See also

• PipeSwitch –Fast Pipelined Context Switching for Deep Learning Applications
• nvshare – Practical GPU Sharing without Memory Size Constraints
• LLaVA: Large Language and Vision Assistant - Part 1
• Vision Transformers - Part 2
• Vision Transformers - Part 1