# Meta-Learner with Linear Nulling

Source: [Meta-Learner with Linear Nulling](<https://www.sota2.com/research/paper/68fa651c1e209131cea0868d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:37.466Z

Authors: Sung Whan Yoon, Jun Seo, Jaekyun Moon

Published: 2018-06-04T08:42:09.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1806.01010>)

[PDF](<https://arxiv.org/pdf/1806.01010.pdf>)