Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning

Open-L2O: A Comprehensive and Reproducible Benchmark for Learning to Optimize Algorithms

pytorch implementation of Optimization as a Model for Few-shot Learning

Personalizing Dialogue Agents via Meta-Learning

Learning to Learn: Gradient-free Optimization framework

"Learning to learn by gradient descent by gradient descent "by PyTorch -- a simple re-implementation.

[CVPR 2020] L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

A modular toolbox for meta-learning research with a focus on speed and reproducibility.

[NeurIPS 2020 Spotlight Oral] "Training Stronger Baselines for Learning to Optimize", Tianlong Chen*, Weiyi Zhang*, Jingyang Zhou, Shiyu Chang, Sijia Liu, Lisa Amini, Zhangyang Wang

Code for "Learning Inductive Biases with Simple Neural Networks" (Feinman & Lake, 2018).

Optim4RL is a Jax framework of learning to optimize for reinforcement learning.

A clean, lightweight and modularized PyTorch meta-learning library.

Task Generation Scheme for the Meta-Unsupervised Algorithm

Learning to learn by gradient descent by gradient descent, Andrychowicz et al., NIPS 2016

Learnig Go with coding exercises

Chrome extension to create tasks based on the spaced repetition concept