[1703.03400] Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status

[1703.03400] Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:1703.03400 (cs) [Submitted on 9 Mar 2017 ( v1 ), last revised 18 Jul 2017 (this version, v3)] Title: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Authors: Chelsea Finn , Pieter Abbeel , Sergey Levine View a PDF of the paper titled Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks, by Chelsea Finn a

related reading

• Meta Learninglilianweng.github.io
• The Scaling Hypothesis · Gwern.netgwern.net
• Just Ask for Generalization | Eric Jangevjang.com
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• The Little Book of Deep Learningfleuret.org
• [2301.08028] A Tutorial on Meta-Reinforcement Learningarxiv.org
• Metalearning or Learning to Learn Since 1987people.idsia.ch
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Bootstrapped Meta-Learningarxiv.org
• Optimizing LLM Test-Time Compute Involves Solving a Meta-RL Problem – Machine Learning Blog | ML@CMU | Carnegie Mellon Universityblog.ml.cmu.edu
• Loss of plasticity in deep continual learning | Naturenature.com
• GitHub - google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models. · GitHubgithub.com