**arXiv ID:** 1807.05076 **Authors:** Tsendsuren Munkhdalai, Adam Trischler **Published:** 2018-07-12T14:40:06Z **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 impleme...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Metalearning With Hebbian Fast Weights?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-metalearning-with-hebbian-fast-weights)
# Metalearning with Hebbian Fast Weights
**arXiv ID:** 1807.05076
**Authors:** Tsendsuren Munkhdalai, Adam Trischler
**Published:** 2018-07-12T14:40:06Z
**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.
## Skill Description
This skill is generated from the arXiv paper: Metalearning with Hebbian Fast Weights (1807.05076).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1807.05076](http://arxiv.org/abs/1807.05076v1)
