Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 28 for “"OPTIMIZATION NEURAL NETWORKS"”.
-
Neural Networks for Data Fusion
… the incorporation of new techniques, such as neural networks and others, will make the data fusion system more powerful in tri-service (command, control, and communications). In this thesis, optimization neural networks are investigated. A new technique of measurement data association in a …
-
Particle swarm optimization in multi-agents cooperation applications
… ( PSO-Network) is put forward to replace Neural Networks in the Intelligent Learning and Reasoning Unit (ILRU). Through simulation, it is shown that the inner-motivated group intelligence is achievable and is efficient in prompting the capacity of multi-agents as a united team.
-
Neural networks for nonlinear programming
Thesis (Ph. D.)--Michigan State University. Department of Electrical Engineering, 1991
-
Artificial neural networks for constrained and unconstrained optimization
Thesis (Ph. D.)--Michigan State University. Department of Electrical Engineering, 1992
-
Towards Optimization and Robustification of Data-Driven Models
… achieved through the use of models such as deep neural networks (DNNs) in various applications. However, complete reliance on intelligent machine learning systems is still a distant dream. Nevertheless, the initial success of data-driven approaches presents a promising path for building …
-
On the performance of optimisation networks / by Brenton S. Cooper.
… thesis examines the performace of optimisation networks. The main objectives are to determine if there exist any factors which limit the solution quality that may be achieved with optimisation networks, to determine the reasons for any such limitations and to suggest remedies for them.
-
ΑΝΑΠΤΥΞΗ ΚΑΙ ΕΦΑΡΜΟΓΗ ΜΗ ΓΡΑΜΜΙΚΩΝ ΔΙΑΝΥΣΜΑΤΙΚΩΝ ΜΕΘΟΔΩΝ ΕΠΕΞΕΡΓΑΣΙΑΣ ΒΙΟΣΗΜΑΤΩΝ
… THEORY - CLUSTERING TECHNIQUES, OPTIMISATION NEURAL NETWORKS, GENETIC ALGORITHMS, SOFT DECISIONS APPROACH - WERE ADOPTED IN ORDER TO GUARANTEE THE RELIABILITY AND COMPUTATIONAL FLEXIBILITY OF THE PROPOSED TECHNIQUES. THE APPLICATION OF THE INTRODUCED TECHNIQUES TO CLINICAL DATA VERIFIED THE …
-
Adversarial Attacks, Coarse Robustness, and Dataless Neural Networks: Novel Techniques for Improved Classification and Combinatorial Optimization
Neural networks (NN) have become a central component in most machine learning systems. However, studies have shown that these models are not robust against adversarial attacks. As such, in this dissertation, we explore four directions. In the first direction, we investigate adversarial attacks on …
-
Merging First-Principles with Machine Learning for the Optimization of Process and Energy Systems
… to increase the speed or accuracy of challenging optimization problems, the use of novel machine-learning architectures for problems that require components with fast on-line prediction, a focus on applications relevant to security and resilience with respect to energy infrastructure, and details …
-
Sequentially Optimized Meshfree Approximation as a New Computation Fluid Dynamics Method
… building of a feed-forward artificial neural network through machine learning to solve the flow problem significantly reduces user interaction and reduces computational cost. This is done by avoiding the creation and inversion of possibly dense block diagonal matrices and by focusing …
-
Improving Explainability and Interpretability of Neural Networks via Hyperparameter-Extended Influence Functions
… applications are validated across diverse neural network settings. In addition, we evaluate the practical feasibility of the proposed framework for large-scale models. Collectively, this work positions sensitivity analysis via hyperparameter-extended influence functions as a practical and …
-
Development and implementation of a multi-agent system for intelligent optimized power plant control.
As the demand for electric power grows and regulations on power plant operation become stricter, the size, and therefore complexity, of new power plant units is increasing while the intricacies of the multiple simultaneous processes that take place to generate electricity require tighter control. …
-
Μη γραμμικές μέθοδοι συζυγών κλίσεων για βελτιστοποίηση και εκπαίδευση νευρωνικών δικτύων
… foundation of new conjugate gradient methods for optimization and on the study of new neural network training algorithms and their applications. We propose two new conjugate gradient methods which are based on modified new secant equations with strong theoretical advantages. Moreover, they have …
-
Optimizing Hidden Neurons in Multilayer Perceptrons with a Hybrid Feature Selection Approach for Classification Tasks
… of hidden neurons in multilayer perceptron (MLP) networks remains an ongoing challenge in the field of machine learning. Our research presents an innovative strategy to address this issue by combining data preprocessing, feature selection by a hybrid method, and a methodical approach to MLP …
-
Landscapes and discriminants of optimization problems
This thesis focuses on two optimization problems: the landscape of the loss function arising in the training of a shallow neural network with polynomial activations, and the SO(2) alignment problem. For the first problem, we provide both positive and negative results regarding the favorability of …
-
Development of a novel stopping technique for optimization
Neural networks are being used widely in areas of process control, pattern recognition, etc. The possibility of improving the efficiency of data utilization in neural network training and automating the decision to stop training, using a novel Steady-state Identifier (SSID) algorithm, have been …
-
Empirical Evaluation of Models Used to Predict Torso Muscle Recruitment Patterns
… models are Sum of Cubed Intensities, Artificial Neural Networks, and Distributed Moment Histogram. These three models were adapted to run using recently published descriptions of the lower back anatomy. To evaluate their effectiveness, the models were compared in terms of their fit to a muscle …
-
Refinery-wide optimization using neural network surrogate models
Process optimization helps operate chemical processes more efficiently. Currently, the state-of-the-art in petroleum refineries is to use nonlinear unit-wide optimizers in conjuction with a linear optimizer to schedule the fiow between different process units. This approach, however, does not …
-
Trust Region Methods for Training Neural Networks
Artificial feed-forward neural networks (ff-ANNs) serve as powerful machine learning models for supervised classification problems. They have been used to solve problems stretching from natural language processing to computer vision. ff-ANNs are typically trained using gradient based approaches, …
-
Integrating Prediction and Portfolio Optimization
The fundamental objective of portfolio optimization is the determination of next period's optimal asset allocation under conditions of uncertainty. In most settings the portfolio optimization inputs, such as risk and return, are unobservable at decision time and must be forecasted using observable …
Page 1 of 2