“Meta Networks”, 2017-03-02 (; backlinks; similar):
Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performance on previously learned ones still presents a challenge to neural network models.
In this work, we introduce a novel meta-learning method, Meta Networks (MetaNet), that learns a meta-level knowledge across tasks and shifts its inductive biases via fast parameterization for rapid generalization.
When evaluated on Omniglot and Mini-ImageNet benchmarks, our MetaNet models achieve a near human-level performance and outperform the baseline approaches by up to 6% accuracy.
We demonstrate several appealing properties of MetaNet relating to generalization and continual learning.
View PDF: