Active Recall Networks for Multiperspectivity Learning through Shared Latent Space Optimization

Theus H. Aspiras, Ruixu Liu, Vijayan K. Asari

2019

Abstract

Given that there are numerous amounts of unlabeled data available for usage in training neural networks, it is desirable to implement a neural network architecture and training paradigm to maximize the ability of the latent space representation. Through multiple perspectives of the latent space using adversarial learning and autoencoding, data requirements can be reduced, which improves learning ability across domains. The entire goal of the proposed work is not to train exhaustively, but to train with multiperspectivity. We propose a new neural network architecture called Active Recall Network (ARN) for learning with less labels by optimizing the latent space. This neural network architecture learns latent space features of unlabeled data by using a fusion framework of an autoencoder and a generative adversarial network. Variations in the latent space representations will be captured and modeled by generation, discrimination, and reconstruction strategies in the network using both unlabeled and labeled data. Performance evaluations conducted on the proposed ARN architectures with two popular datasets demonstrated promising results in terms of generative capabilities and latent space effectiveness. Through the multiple perspectives that are embedded in ARN, we envision that this architecture will be incredibly versatile in every application that requires learning with less labels.

Paper Citation

in Harvard Style

Aspiras T., Liu R. and Asari V. (2019). Active Recall Networks for Multiperspectivity Learning through Shared Latent Space Optimization. In Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - Volume 1: NCTA; ISBN 978-989-758-384-1, SciTePress, pages 434-443. DOI: 10.5220/0008369304340443

in Bibtex Style

@conference{ncta19,
author={Theus H. Aspiras and Ruixu Liu and Vijayan K. Asari},
title={Active Recall Networks for Multiperspectivity Learning through Shared Latent Space Optimization},
booktitle={Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - Volume 1: NCTA},
year={2019},
pages={434-443},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008369304340443},
isbn={978-989-758-384-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) - Volume 1: NCTA
TI - Active Recall Networks for Multiperspectivity Learning through Shared Latent Space Optimization
SN - 978-989-758-384-1
AU - Aspiras T.
AU - Liu R.
AU - Asari V.
PY - 2019
SP - 434
EP - 443
DO - 10.5220/0008369304340443
PB - SciTePress