Document Type
Article
Publication Date
2019
Publication Source
IJCCI: Proceedings of the 11th International Joint Conference on Computational Intelligence
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.
Inclusive pages
434-443
ISBN/ISSN
978-989-758-384-1
Document Version
Published Version
Publisher
SciTe Press
Peer Reviewed
yes
eCommons Citation
Aspiras, Theus; Liu, Ruixu; and Asari, Vijayan K., "Active Recall Networks for Multiperspectivity Learning through Shared Latent Space Optimization" (2019). Electrical and Computer Engineering Faculty Publications. 462.
https://ecommons.udayton.edu/ece_fac_pub/462
Included in
Computer Engineering Commons, Electrical and Electronics Commons, Electromagnetics and Photonics Commons, Optics Commons, Other Electrical and Computer Engineering Commons, Systems and Communications Commons
Comments
This open-access article is provided for download in compliance with the publisher’s policy on self-archiving. To view the version of record, use the DOI: https://doi.org/10.5220/0008369304340443