3 citations · 4 across the 5 of their papers we have counts for
6 papers
Parallel Implementation of Distributed Global Optimization (DGO)
Homayoun Valafar, Okan K. Ersoy, Farmaraz Valafar
Parallel implementations of distributed global optimization (DGO) [13] on MP-1 and NCUBE parallel computers revealed an approximate O(n) increase in the performance of this algorit…
Distributed Global Optimization (DGO)
Homayoun Valafar, Okan K. Ersoy, Faramarz Valafar
A new technique of global optimization and its applications in particular to neural networks are presented. The algorithm is also compared to other global optimization algorithms s…
Parallel, Self Organizing, Consensus Neural Networks
Homayoun Valafar, Faramarz Valafar, Okan Ersoy
A new neural network architecture (PSCNN) is developed to improve performance and speed of such networks. The architecture has all the advantages of the previous models such as sel…
Probabilistic Diagnostic Tests for Degradation Problems in Supervised Learning
Gustavo A. Valencia-Zapata, Carolina Gonzalez-Canas, Michael G. Zentner +2
Several studies point out different causes of performance degradation in supervised machine learning. Problems such as class imbalance, overlapping, small-disjuncts, noisy labels,…
Ladder Networks for Semi-Supervised Hyperspectral Image Classification
Julian Büchel, Okan Ersoy
We used the Ladder Network [Rasmus et al. (2015)] to perform Hyperspectral Image Classification in a semi-supervised setting. The Ladder Network distinguishes itself from other sem…
Nonlinear Dynamic Field Embedding: On Hyperspectral Scene Visualization
Dalton Lunga 'and' Okan Ersoy
Graph embedding techniques are useful to characterize spectral signature relations for hyperspectral images. However, such images consists of disjoint classes due to spatial detail…