Meta Networks

03/02/2017
by   Tsendsuren Munkhdalai, et al.
0

Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performances on previously learned ones still presents a significant challenge to neural network models. In this work, we introduce a novel meta learning method, Meta Networks (MetaNet), that learns a meta-level knowledge across tasks and shifts its inductive biases via fast parameterization for rapid generalization. When evaluated on Omniglot and Mini-ImageNet benchmarks, our MetaNet models achieve a near human-level performance and outperform the baseline approaches by up to 6 generalization and continual learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/01/2020

Meta-Consolidation for Continual Learning

The ability to continuously learn and adapt itself to new tasks, without...
research
10/27/2021

Learning where to learn: Gradient sparsity in meta and continual learning

Finding neural network weights that generalize well from small datasets ...
research
09/17/2020

Few-Shot Unsupervised Continual Learning through Meta-Examples

In real-world applications, data do not reflect the ones commonly used f...
research
03/06/2021

Learning to Continually Learn Rapidly from Few and Noisy Data

Neural networks suffer from catastrophic forgetting and are unable to se...
research
01/28/2021

Generalising via Meta-Examples for Continual Learning in the Wild

Learning quickly and continually is still an ambitious task for neural n...
research
07/15/2023

Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks

In this work, we propose a novel prior learning method for advancing gen...
research
09/04/2022

Generalization in Neural Networks: A Broad Survey

This paper reviews concepts, modeling approaches, and recent findings al...

Please sign up or login with your details

Forgot password? Click here to reset