Metalearning with Hebbian Fast Weights
Neural and Evolutionary Computing
2018-07-16 v1 Artificial Intelligence
Machine Learning
Machine Learning
Abstract
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.
Cite
@article{arxiv.1807.05076,
title = {Metalearning with Hebbian Fast Weights},
author = {Tsendsuren Munkhdalai and Adam Trischler},
journal= {arXiv preprint arXiv:1807.05076},
year = {2018}
}
Comments
8 pages, 3 figures, 4 tables. arXiv admin note: text overlap with arXiv:1712.09926