Meta-Learning: Learning to Learn Fast
Meta-learning, also known as “learning to learn”, intends to design models that can learn new skills or adapt to new environments rapidly with a few training examples. There are three common approaches: 1) learn an efficient distance metric (metric-based); 2) use (recurrent) network with external or internal memory (model-based); 3)...
[Updated on 2019-10-01: thanks to Tianhao, we have this post translated in Chinese!] A good machine learning model often requires training with a large number of samples. Humans, in contrast, learn new concepts and skills much faster and more efficiently. Kids who have seen cats and birds only a few times can quickly tell them apart. People who know how to ride a bike are likely to discover the way to ride a motorcycle fast with little or even no demonstration. Is it possible to design a machine learning model with similar properties — learning new concepts and skills fast with a few…
saved by
related reading
- A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
- Optimizing LLM Test-Time Compute Involves Solving a Meta-RL Problem – Machine Learning Blog | ML@CMU | Carnegie Mellon Universityblog.ml.cmu.edu
- why don’t we explicitly train models to be good at generalization?substack.com
- NL.pdfabehrouz.github.io
- A Recipe for Training Neural Networkskarpathy.github.io
- Just Ask for Generalization | Eric Jangevjang.com
- Bootstrapped Meta-Learningarxiv.org
- The Continual Learning Problemjessylin.com
- Metalearning or Learning to Learn Since 1987people.idsia.ch
- [1906.01820] Risks from Learned Optimization in Advanced Machine Learning Systemsarxiv.org
- You can’t imitation-learn how to continual-learn — LessWronglesswrong.com
- Bayesian Neural Networkscs.toronto.edu