Augmented Memory Networks for Streaming-Based Active One-Shot Learning

09/04/2019
by   Andreas Kvistad, et al.
0

One of the major challenges in training deep architectures for predictive tasks is the scarcity and cost of labeled training data. Active Learning (AL) is one way of addressing this challenge. In stream-based AL, observations are continuously made available to the learner that have to decide whether to request a label or to make a prediction. The goal is to reduce the request rate while at the same time maximize prediction performance. In previous research, reinforcement learning has been used for learning the AL request/prediction strategy. In our work, we propose to equip a reinforcement learning process with memory augmented neural networks, to enhance the one-shot capabilities. Moreover, we introduce Class Margin Sampling (CMS) as an extension of the standard margin sampling to the reinforcement learning setting. This strategy aims to reduce training time and improve sample efficiency in the training process. We evaluate the proposed method on a classification task using empirical accuracy of label predictions and percentage of label requests. The results indicates that the proposed method, by making use of the memory augmented networks and CMS in the training process, outperforms existing baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/12/2018

Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning

Active learning (AL) aims to enable training high performance classifier...
research
11/15/2022

MEAL: Stable and Active Learning for Few-Shot Prompting

Few-shot classification in NLP has recently made great strides due to th...
research
11/15/2018

Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks

Deep neural networks have shown superior performance in many regimes to ...
research
01/29/2019

Limitations of Assessing Active Learning Performance at Runtime

Classification algorithms aim to predict an unknown label (e.g., a quali...
research
05/31/2019

Minimum-Margin Active Learning

We present a new active sampling method we call min-margin which trains ...
research
04/11/2016

Active Learning for Online Recognition of Human Activities from Streaming Videos

Recognising human activities from streaming videos poses unique challeng...
research
04/28/2020

Learned Garbage Collection

Several programming languages use garbage collectors (GCs) to automatica...

Please sign up or login with your details

Forgot password? Click here to reset