Rapid Adaptation with Conditionally Shifted Neurons

Autor:	Munkhdalai, Tsendsuren, Yuan, Xingdi, Mehri, Soroush, Trischler, Adam
Rok vydání:	2017
Předmět:	Computer Science - Machine Learning Computer Science - Neural and Evolutionary Computing Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: ICML 2018; Added: additional ablation and speed comparison with MetaNet
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1712.09926 Zobrazit plný text záznamu View this record from Arxiv