Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Publication
- Publication Type
Articles 1 - 5 of 5
Full-Text Articles in Physical Sciences and Mathematics
Implementation Of Multivariate Artificial Neural Networks Coupled With Genetic Algorithms For The Multi-Objective Property Prediction And Optimization Of Emulsion Polymers, David Chisholm
Master's Theses
Machine learning has been gaining popularity over the past few decades as computers have become more advanced. On a fundamental level, machine learning consists of the use of computerized statistical methods to analyze data and discover trends that may not have been obvious or otherwise observable previously. These trends can then be used to make predictions on new data and explore entirely new design spaces. Methods vary from simple linear regression to highly complex neural networks, but the end goal is similar. The application of these methods to material property prediction and new material discovery has been of high interest …
Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods, Christof Teuscher
Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods, Christof Teuscher
Student Research Symposium
In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the evaluation of …
Rvm Soft Sensing Model Based On Optimized Combined Kernel Function, Yanan Zhang, Huizhong Yang
Rvm Soft Sensing Model Based On Optimized Combined Kernel Function, Yanan Zhang, Huizhong Yang
Journal of System Simulation
Abstract: An RVM spft sensingmodeling method based onthe optimizedcombined kernel functionis proposed.In order to simultaneously get better prediction and sparsity, a fitness function synthesizing regression accuracy and sparsity is created while constructing a combined kernel functionfor RVM.The genetic algorithm is used to optimize the weights and kernel parametersof the RVMcombined kernel.The proposed method is used totomodela cleavage-recovery unit in the production process of Bisphenol-A.The results show that it can guarantee better sparsity andregression accuracy than the general SVM combinedkernel model andGA-RVM single kernel model.
Ingan/Gan Tandem Solar Cell Parameter Estimation: A Comparative Stud, Abdelmoumene Benayad, Smail Berrah
Ingan/Gan Tandem Solar Cell Parameter Estimation: A Comparative Stud, Abdelmoumene Benayad, Smail Berrah
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, two hybrid estimation approaches, hybrid genetic algorithm (TR-GA) and hybrid particle swarm optimization (TR-PSO), are used to estimate single-diode model InGaN/GaN solar cell parameters from J?V experimental data under AM0 illumination. These parameters are photocurrent density ($J_{ph}$), reverse saturation current density ($J_{s}$), ideality factor ($A$), series resistance ($R_{s}$), and shunt resistance ($R_{sh}$). The trust region (TR) method used in both approaches provides the initial conditions and helps to avoid the problem of premature convergence (due to local minimum). Simulation results based on the minimization of the mean square error between experimental and theoretical J-V characteristics show that …
Computational Modeling Of Trust Factors Using Reinforcement Learning, C. M. Kuzio, A. Dinh, C. Stone, L. Vidyaratne, K. M. Iftekharuddin
Computational Modeling Of Trust Factors Using Reinforcement Learning, C. M. Kuzio, A. Dinh, C. Stone, L. Vidyaratne, K. M. Iftekharuddin
Electrical & Computer Engineering Faculty Publications
As machine-learning algorithms continue to expand their scope and approach more ambiguous goals, they may be required to make decisions based on data that is often incomplete, imprecise, and uncertain. The capabilities of these models must, in turn, evolve to meet the increasingly complex challenges associated with the deployment and integration of intelligent systems into modern society. Historical variability in the performance of traditional machine-learning models in dynamic environments leads to ambiguity of trust in decisions made by such algorithms. Consequently, the objective of this work is to develop a novel computational model that effectively quantifies the reliability of autonomous …