Can I read Meta-Learner with Linear Nulling on EtoBox?

Meta-Learner with Linear Nulling by Yoon, Sung Whan; Seo, Jun; Moon, Jaekyun is a scholarly article available to read on EtoBox.

What is Meta-Learner with Linear Nulling about?

We propose a meta-learning algorithm utilizing a linear transformer that carries out null-space projection of neural network outputs. The main idea is to construct an alternative classification space such that the error signals during few-shot learning are quickly zero-forced on that space so that reliable classification on low data is possible. The final decision on a query is obtained utilizing a null-space-projected distance measure between the network output and reference vectors, both of which have been trained in the initial learning phase. Among the known methods with a given model size, our meta-learner achieves the best or near-best image classification accuracies with Omniglot and miniImageNet datasets.

Author

Yoon, Sung Whan; Seo, Jun; Moon, Jaekyun

Published

2018

Language

EN