LGMLMar 2, 2017

Meta Networks

arXiv:1703.00837v21152 citations
AI Analysis

This addresses the problem of few-shot learning for neural networks, enabling better adaptation to new tasks with limited data, which is incremental as it builds on existing meta-learning methods.

The paper tackles the challenge of rapid generalization on new concepts with small training data while preserving performance on previously learned tasks, achieving near human-level performance and outperforming baseline approaches by up to 6% accuracy on Omniglot and Mini-ImageNet benchmarks.

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 performances on previously learned ones still presents a significant 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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes