综述
- Meta-Learning: A Survey
- Meta-learning algorithms for Few-Shot Computer Vision
- Metalearning: a survey of trends and technologies
基础算法
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Reptile: a Scalable Metalearning Algorithm
- Fast Context Adaptation via Meta-Learning
- Adversarial Meta-Learning
- Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
- Reconciling meta-learning and continual learning
with online mixtures of tasks
- MetaGAN: An Adversarial Approach to Few-Shot Learning
- Auto-Meta: Automated Gradient Based Meta Learner Search
- Learned Optimizers that Scale and Generalize
元强化学习
- Generalizing Skills with Semi-Supervised Reinforcement Learning
应用
视觉应用
- FIGR: Few-shot Image Generation with Reptile
- Fast Parameter Adaptation for Few-shot Image Captioning and Visual Question Answering
其它应用
- MIND: Model Independent Neural Decoder
数据集
视频课程
- 斯坦福CS330 - 深度多任务学习和元学习
- 李宏毅课程
- Hugo Larochelle: Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead
- Chelsea Finn: Building Unsupervised Versatile Agents with Meta-Learning
书籍
- Hands-On Meta Learning with Python: Meta learning using one-shot learning, MAML, Reptile, and Meta-SGD with TensorFlow
代码
领域专家
初步版本,水平有限,有错误或者不完善的地方,欢迎大家提建议和补充,会一直保持更新,本文为专知内容组原创内容,未经允许不得转载,如需转载请发送邮件至fangquanyi@gmail.com 或 联系微信专知小助手(Rancho_Fang)
敬请关注http://www.zhuanzhi.ai 和关注专知公众号,获取第一手AI相关知识
最近更新:2019-12-10