[2401.08623] Wake-Sleep Consolidated Learning

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 Get status notifications via email or slack

[2401.08623] Wake-Sleep Consolidated Learning --> Computer Science > Neural and Evolutionary Computing arXiv:2401.08623 (cs) [Submitted on 6 Dec 2023] Title: Wake-Sleep Consolidated Learning Authors: Amelia Sorrenti , Giovanni Bellitto , Federica Proietto Salanitri , Matteo Pennisi , Simone Palazzo , Concetto Spampinato View a PDF of the paper titled Wake-Sleep Consolidated Learning, by Amelia Sorrenti and 5 other authors View PDF HTML (experimental) Abstract: We propose Wake-Sleep Consolidated Learning (WSCL), a learning strategy leveraging Complementary Learning System theory and the wake-sl

saved by

• Arjuna Tillekeratne

related reading

• NL.pdfabehrouz.github.io
• Loss of plasticity in deep continual learning | Naturenature.com
• Why We Need Continual Learning | Andreessen Horowitza16z.com
• [1606.09282] Learning without Forgettingarxiv.org
• The Continual Learning Problemjessylin.com
• Learning without Forgettingarxiv.org
• ws.pdfcs.toronto.edu
• Keynote & Tutorial – Continual Learning and Catastrophic Forgetting2024.ccneuro.org
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Do Language Models Need Sleep? Offline Recurrence for Improved Online Inferencearxiv.org
• So how does learning work?cs.mcgill.ca
• Good sleep, good learning, good lifesuper-memory.com