Comparing ensemble strategies for deep learning: An application to facial expression recognition
Recent works have shown that Convolutional Neural Networks (CNNs), because of their
effectiveness in feature extraction and classification tasks, are suitable tools to address the …
effectiveness in feature extraction and classification tasks, are suitable tools to address the …
Neural networks for metamodelling the hygrothermal behaviour of building components
When simulating the hygrothermal behaviour of a building component, there are many
inherently uncertain parameters. A probabilistic evaluation takes these uncertainties into …
inherently uncertain parameters. A probabilistic evaluation takes these uncertainties into …
Toward better accuracy-efficiency trade-offs: Divide and co-training
The width of a neural network matters since increasing the width will necessarily increase
the model capacity. However, the performance of a network does not improve linearly with …
the model capacity. However, the performance of a network does not improve linearly with …
A linear model based on Kalman filter for improving neural network classification performance
Neural network has been applied in several classification problems such as in medical
diagnosis, handwriting recognition, and product inspection, with a good classification …
diagnosis, handwriting recognition, and product inspection, with a good classification …
Effective neural network ensemble approach for improving generalization performance
J Yang, X Zeng, S Zhong, S Wu - IEEE transactions on neural …, 2013 - ieeexplore.ieee.org
This paper, with an aim at improving neural networks' generalization performance, proposes
an effective neural network ensemble approach with two novel ideas. One is to apply neural …
an effective neural network ensemble approach with two novel ideas. One is to apply neural …
Listed companies' financial distress prediction based on weighted majority voting combination of multiple classifiers
How to effectively predict financial distress is an important problem in corporate financial
management. Though much attention has been paid to financial distress prediction methods …
management. Though much attention has been paid to financial distress prediction methods …
Knowledge discovery from remote sensing images: A review
L Wang, J Yan, L Mu, L Huang - Wiley Interdisciplinary Reviews …, 2020 - Wiley Online Library
The development of Earth observation (EO) technology has made the volume of remote
sensing data archiving continually larger, but the knowledge hidden in massive remote …
sensing data archiving continually larger, but the knowledge hidden in massive remote …
Improving optimization of convolutional neural networks through parameter fine-tuning
N Becherer, J Pecarina, S Nykl… - Neural Computing and …, 2019 - Springer
In recent years, convolutional neural networks have achieved state-of-the-art performance in
a number of computer vision problems such as image classification. Prior research has …
a number of computer vision problems such as image classification. Prior research has …
Ensemble models based on QuBiLS-MAS features and shallow learning for the prediction of drug-induced liver toxicity: improving deep learning and traditional …
JR Mora, Y Marrero-Ponce… - Chemical Research …, 2020 - ACS Publications
Drug-induced liver injury (DILI) is a key safety issue in the drug discovery pipeline and a
regulatory concern. Thus, many in silico tools have been proposed to improve the …
regulatory concern. Thus, many in silico tools have been proposed to improve the …
Convolutional neural network for copy-move forgery detection
Digital image forgery is a growing problem due to the increase in readily-available
technology that makes the process relatively easy. In response, several approaches have …
technology that makes the process relatively easy. In response, several approaches have …