Meta-Learning with Implicit Gradients

iMAML：使用L2正则化增加内部梯度更新次数.

A critical analysis of self-supervision, or what we can learn from a single image

使用单张图像进行自监督学习.

Faster Neural Network Training with Data Echoing

Data Echoing：一种加速模型训练的方法.

Concept Learning with Energy-Based Models

使用能量模型进行概念学习.

Big Transfer (BiT): General Visual Representation Learning

BiT：用于迁移学习的预训练卷积神经网络模型.

Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning

分治的蒙特卡洛树搜索解决目标导向的强化学习问题.