Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Unsupervised learning from limited available data by β-NMF and dual autoencoder

Abstract: 

Unsupervised Learning (UL) models are a class of Machine Learning (ML) which concerns with reducing dimensionality, data factorization, disentangling and learning the representations among the data. The UL models gain their popularity due to their abilities to learn without any predefined label, and they are able to reduce the noise and redundancy among the data samples. However, generalizing the UL models for different applications including image generation, compression, encoding, and recognition faces different challenges due to limited available data for learning, diversity, and complex dimensions. To overcome such challenges, we propose a partial learning procedure by utilizing the β-Non Negative Matrix Factorization (β-NMF), which maps the data into two complementary subspaces constituting generalized driven priors among the data. Moreover, we employ a dual-shallow Autoencoder (AE) to learn the subspaces separately or jointly for image reconstruction and visualization tasks, where our model performance shows superior results to the literary works when learning the model with a small amount of data and generalizing it for large-scale unseen data.

up
0 users have voted:

Paper Details

Authors:
Mohanad Abukmeil,Stefano Ferrari, Vincenzo Piuri, Fabio Scotti
Submitted On:
6 November 2020 - 4:26am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Mohanad Abukmeil
Paper Code:
SMR-03.5
Document Year:
2020
Cite

Document Files

Unsupervised learning from limited available data by β-NMF and dual autoencoder (final published).pdf

(9)

Subscribe

[1] Mohanad Abukmeil,Stefano Ferrari, Vincenzo Piuri, Fabio Scotti, "Unsupervised learning from limited available data by β-NMF and dual autoencoder", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5545. Accessed: Nov. 29, 2020.
@article{5545-20,
url = {http://sigport.org/5545},
author = {Mohanad Abukmeil;Stefano Ferrari; Vincenzo Piuri; Fabio Scotti },
publisher = {IEEE SigPort},
title = {Unsupervised learning from limited available data by β-NMF and dual autoencoder},
year = {2020} }
TY - EJOUR
T1 - Unsupervised learning from limited available data by β-NMF and dual autoencoder
AU - Mohanad Abukmeil;Stefano Ferrari; Vincenzo Piuri; Fabio Scotti
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5545
ER -
Mohanad Abukmeil,Stefano Ferrari, Vincenzo Piuri, Fabio Scotti. (2020). Unsupervised learning from limited available data by β-NMF and dual autoencoder. IEEE SigPort. http://sigport.org/5545
Mohanad Abukmeil,Stefano Ferrari, Vincenzo Piuri, Fabio Scotti, 2020. Unsupervised learning from limited available data by β-NMF and dual autoencoder. Available at: http://sigport.org/5545.
Mohanad Abukmeil,Stefano Ferrari, Vincenzo Piuri, Fabio Scotti. (2020). "Unsupervised learning from limited available data by β-NMF and dual autoencoder." Web.
1. Mohanad Abukmeil,Stefano Ferrari, Vincenzo Piuri, Fabio Scotti. Unsupervised learning from limited available data by β-NMF and dual autoencoder [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5545