Work

Episode-Based Active Learning with Bayesian Neural Networks

Year: 2017

Type: preprint

Abstract: We investigate different strategies for active learning with Bayesian deep neural networks. We focus our analysis on scenarios where new, unlabeled data is obtained episodically, such as commonly encountered in mobile robotics applications. An evaluation of different strategies for acquisition, updating, and final training on the CIFAR-10 dataset shows that incremental network updates with final training on the accumulated acquisition set are essential for best performance, while limiting the amount of required human labeling labor.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1703.07473

Authors: Dayoub, Feras, Sünderhauf, Niko, Corke, Peter

Institutions: Queensland University of Technology, Australian Centre for Robotic Vision

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Australian Centre for Robotic Vision

Award: G252308265

OpenAlex ID: W2949909993

Cites: 4

Cited by: 1

Related to: 20