Hyperparameter optimization in learning systems
R Andonie - Journal of Membrane Computing, 2019 - Springer
While the training parameters of machine learning models are adapted during the training
phase, the values of the hyperparameters (or meta-parameters) have to be specified before …
phase, the values of the hyperparameters (or meta-parameters) have to be specified before …
Impact of dataset size on classification performance: an empirical evaluation in the medical domain
Dataset size is considered a major concern in the medical domain, where lack of data is a
common occurrence. This study aims to investigate the impact of dataset size on the overall …
common occurrence. This study aims to investigate the impact of dataset size on the overall …
A survey of adaptive resonance theory neural network models for engineering applications
This survey samples from the ever-growing family of adaptive resonance theory (ART)
neural network models used to perform the three primary machine learning modalities …
neural network models used to perform the three primary machine learning modalities …
Extreme data mining: Inference from small datasets
R Andonie - International Journal of Computers …, 2010 - digitalcommons.cwu.edu
Neural networks have been applied successfully in many fields. However, satisfactory
results can only be found under large sample conditions. When it comes to small training …
results can only be found under large sample conditions. When it comes to small training …
An insect classification analysis based on shape features using quality threshold ARTMAP and moment invariant
SN Yaakob, L Jain - Applied Intelligence, 2012 - Springer
The main objective of this paper is to investigate the use of Quality Threshold ARTMAP
(QTAM) neural network in classifying the feature vectors generated by moment invariant for …
(QTAM) neural network in classifying the feature vectors generated by moment invariant for …
Pretrained back propagation based adaptive resonance theory network for adaptive learning
C Zhang, C Jiang, Q Xu - Journal of Algorithms & …, 2023 - journals.sagepub.com
The deep convolutional neural network performs well in current computer vision tasks.
However, most of these models are trained on an aforehand complete dataset. New …
However, most of these models are trained on an aforehand complete dataset. New …
A Hybrid ART-GRNN Online Learning Neural Network With a -Insensitive Loss Function
In this brief, a new neural network model called generalized adaptive resonance theory
(GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive …
(GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive …
An investigation of the suitability of Artificial Neural Networks for the prediction of core and local skin temperatures when trained with a large and gender-balanced …
K Michael, MDP Garcia-Souto, P Dabnichki - Applied Soft Computing, 2017 - Elsevier
Neural networks have been proven to successfully predict the results of complex non-linear
problems in a variety of research fields, including medical research. Yet there is paucity of …
problems in a variety of research fields, including medical research. Yet there is paucity of …
Fuzzy ARTMAP prediction of biological activities for potential HIV-1 protease inhibitors using a small molecular data set
R Andonie, L Fabry-Asztalos… - IEEE/ACM …, 2009 - ieeexplore.ieee.org
Obtaining satisfactory results with neural networks depends on the availability of large data
samples. The use of small training sets generally reduces performance. Most classical …
samples. The use of small training sets generally reduces performance. Most classical …
Managing category proliferation in fuzzy ARTMAP caused by overlapping classes
WY Sit, LO Mak, GW Ng - IEEE transactions on neural networks, 2009 - ieeexplore.ieee.org
This paper addresses the difficulties brought about by overlapping classes in fuzzy ARTMAP
(FAM). Training with such data leads to category proliferation, and classification is made …
(FAM). Training with such data leads to category proliferation, and classification is made …