NEAILGMLJul 12, 2018

Metalearning with Hebbian Fast Weights

arXiv:1807.05076v143 citations
Originality Incremental advance
AI Analysis

This addresses the problem of rapid adaptation to new tasks with limited data for machine learning systems, representing an incremental improvement over existing methods.

The paper tackled one-shot learning by unifying neural approaches with associative memory, achieving state-of-the-art results on benchmarks like Omniglot, Mini-ImageNet, and Penn Treebank.

We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds representations via slow weights, learned across tasks through SGD, while fast weights constructed by a Hebbian learning rule implement one-shot binding for each new task. On the Omniglot, Mini-ImageNet, and Penn Treebank one-shot learning benchmarks, our model achieves state-of-the-art results.

Foundations

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

Your Notes