# Rapid Adaptation with Conditionally Shifted Neurons

arXiv: https://arxiv.org/abs/1712.09926 · HTML: https://mlsanity.com/paper/1712.09926/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2017.

## Built on by (most cited first, 2 of 2)

- [AdaEmbed: Semi-supervised Domain Adaptation in the Embedding Space](https://mlsanity.com/paper/2401.12421/) (2024)
- [A Transductive Maximum Margin Classifier for Few-Shot Learning](https://mlsanity.com/paper/2107.11975/) (2021)

## Abstract (arXiv)

We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework of metalearning, where the aim is to replicate some of the flexibility of human learning in machines. Conditionally shifted neurons modify their activation values with task-specific shifts retrieved from a memory module, which is populated rapidly based on limited task experience. On metalearning benchmarks from the vision and language domains, models augmented with conditionally shifted neurons achieve state-of-the-art results.