Energy-Based Models for Continual Learning
energy-based-model.github.io · 730 words · saved by 1 readers
Energy-Based Models for Continual Learning
Energy-Based Models for Continual Learning --> Energy-Based Models for Continual Learning ICML 2021 --> Shuang Li 1 , Yilun Du 1 , Gido M. van de Ven 2 , Igor Mordatch 3 1 MIT CSAIL 2 Baylor College of Medicine 3 Google Brain Paper Code We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs change the underlying training objective to causes less interference with previously learned information. Our proposed version of EBMs for continual lear
related reading
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- The Continual Learning Problemjessylin.com
- Energy-Based Modelsenergy-based-model.github.io
- pdfopenreview.net
- Continual Learning Bench 1.0 — Newscontinual-learning-bench.com
- Self-Distillation Enables Continual Learningarxiv.org
- NL.pdfabehrouz.github.io
- Loss of plasticity in deep continual learning | Naturenature.com
- Supermemory — Memory and continual learning for agentssupermemory.ai
- What are the real problems of continual learning?infinitefaculty.substack.com
- Announcing our investment in Engram, the memory dream team — Amplify Partnersamplifypartners.com
- David Duvenaudcs.toronto.edu