Meta-Learning
1169 papers with code • 4 benchmarks • 19 datasets
Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.
( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )
Libraries
Use these libraries to find Meta-Learning models and implementationsDatasets
Most implemented papers
How to train your MAML
The field of few-shot learning has recently seen substantial advancements.
Meta Pseudo Labels
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90. 2% on ImageNet, which is 1. 6% better than the existing state-of-the-art.
Learning to learn by gradient descent by gradient descent
The move from hand-designed features to learned features in machine learning has been wildly successful.
Learning to reinforcement learn
We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors.
LEAF: A Benchmark for Federated Settings
Modern federated networks, such as those comprised of wearable devices, mobile phones, or autonomous vehicles, generate massive amounts of data each day.
Meta-Learning with Differentiable Convex Optimization
We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks.
ProMP: Proximal Meta-Policy Search
Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood.
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
In order to create a personalized talking head model, these works require training on a large dataset of images of a single person.
Meta-Learning Representations for Continual Learning
We show that it is possible to learn naturally sparse representations that are more effective for online updating.