有哪些比较好的元学习（meta learning）领域的学习资源？ 第1页

元学习（meta learning）的学习资料，你要的全都有~

科普介绍

科普视频：Meta Learning by Siraj Raval

知乎专栏：智能单元

Meta Learning单排小教学
百家争鸣的Meta Learning/Learning to learn
荐读 Meta-Learning in Neural Networks: A survey
Chelsea Finn博士论文赏析 Learning to Learn with Gradients

博客

• 大数据时代的小样本深度学习问题的综述
• Berkeley Artificial Intelligence Research blog
• Meta-Learning: Learning to Learn Fast
• Meta-Reinforcement Learning
• How to train your MAML: A step by step approach
• An Introduction to Meta-Learning
• From zero to research — An introduction to Meta-learning
• What’s New in Deep Learning Research: Understanding Meta-Learning
• Meta Reinforcement Learning Blog by Lilian Weng
• Meta-Learning: Learning to Learn Fast

领域学者

• Chelsea Finn, UC Berkeley

• Pieter Abbeel, UC Berkeley
• Erin Grant, UC Berkeley
• Raia Hadsell, DeepMind
• Misha Denil, DeepMind
• Adam Santoro, DeepMind
• Sachin Ravi, Princeton University
• David Abel, Brown University
• Brenden Lake, Facebook AI Research

领域综述

（这里先放一篇小样本学习的领域综述）

Generalizing from a Few Examples: A Survey on Few-Shot Learning

解读1 解读2 解读3

作者： QUANMING YAO

小样本学习（Few-shot Learning）综述 （阿里巴巴智能服务事业部小蜜北京团队）

领域经典文献

（正在调研）

论文+展示视频

NeurIPS2019

Yoshua Bengio: Meta-learning

West Ballroom B - Meta-Learning （12个talk）

系列视频课程

Chelsea Finn

斯坦福CS330

Stanford CS330课程 深度多任务和元学习 / B站视频（中英字幕）

ICML 2019 Tutorial：Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning

B站视频 （2个视频）

Building Unsupervised Versatile Agents with Meta-Learning

Invited Talks

a talk on challenges in multi-task learning and meta-learning (slides here, video here) at the IAS Workshop on New Directions in Optimization Statistics and Machine Learning.

NeurIPS 2019：an invited talk on Meta-Learning and Memorization (slides here, video here) at the Bayesian Deep Learning Workshop

In July 2018, gave a talk at Google DeepMind with Sergey Levine on meta-learning frontiers. (slides here)
At NIPS 2017, I gave an invited talk in the Workshop on Meta-Learning (slides here) and contributed talks at the Deep Reinforcement Learning Symposium and the workshop on Deep Learning: Bridging Theory and Practice.

李宏毅机器学习2020春季课程（中文）

李宏毅机器学习（2020春季课程） / B站视频地址

Meta-Learning MAML 课件

Meta Learning - Gradient Descent and Metric-based 课件

Google Brain: Hugo Larochelle 小样本学习

Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead B站视频 / 课件

Generalizing from Few Examples with Meta-Learning B站视频 / 课件

Massimiliano Patacchiola 小样本学习

B站视频 （7个视频） / 课程主页

其他课程

• Sam Ritter: Meta-Learning to Make Smart Inferences from Small Data
• Model Agnostic Meta Learning by Siavash Khodadadeh
• Meta Learning and One-Shot Learning

数据集

Most popularly used datasets：

• Omniglot
• mini-ImageNet
• ILSVRC
• FGVC aircraft
• Caltech-UCSD Birds-200-2011

使用谷歌查询其他元学习相关数据集 here

其他数据集整合结果 datasets

论文与代码

论文集参见：Awesome-Meta-Learning / Floodsung's Meta-Learning Paper lists

Meta-Learning in Neural Networks: A Survey

few-shot-object-detection

每年cvpr都会有针对小样本学习的一个总结

比如：从 CVPR 2019 一览小样本学习研究进展

ICLR2019: A CLOSER LOOK AT FEW-SHOT CLASSIFICATION

A Baseline for Few-Shot Image Classification

书籍

• Hands-On Meta Learning with Python: Meta learning using one-shot learning, MAML, Reptile, and Meta-SGD with TensorFlow, (2019), Sudharsan Ravichandiran. [pdf] [code]

Workshops

NeurIPS

• MetaLearn 2019
• MetaLearn 2018
• MetaLearn 2017

参考资料：

https:// github.com/sudharsan132 96/Awesome-Meta-Learning
https:// github.com/Duan-JM/awes ome-papers-fewshot
https:// github.com/tata1661/Few ShotPapers

注：调研时间：2020年6月10日
由于知乎编辑器限制，PDF在此处不太好展示，可以在 个人博客 看完整版