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 146 for “"Networks, Neural"”.
-
Τεχνικές καθολικής βελτιστοποίησης
… fields, such as medicine, industry, business, networks, neural models, etc. In this dissertation, the focus is on finding optimal solutions in mathematical models, known as objective functions or test functions or benchmark functions. In many stochastic methods, different initial distributions …
-
Evaluating the Intrinsic Similarity between Neural Networks
… that aligns the topological structures of two neural networks. Neural networks are considered to be a black box, because neural networks contain complex model surface determined by their weights that combine attributes non-linearly. Two networks that make similar predictions on training data …
-
A Deep Learning Framework for Complex Engineering Systems via Imbalanced Feature Learning
… and has found applications in many fields. Neural networks are sometimes referred to as “universal function approximators” for their ability to learn complex problems that are otherwise difficult to solve. In engineering, there are complex, time-consuming problems that can be solved by …
-
Two novel ensemble approaches for improving classification of neural networks
… have been developed to this end, such as neural networks. Neural networks are excellent pattern classifiers with very robust means of learning and a relatively high classification power. Naturally, there has been an increasing interest in further improving neural networks’ classification …
-
Higher-order neural networks for invariant pattern recognition
… scaled and rotated patterns using third-order neural networks. Neural networks exhibit poor performance if the input image is transformed by one or a combination of transformations. Training with a large number of transformed patterns, extracting the invariant features before training or using …
-
Invariance and Invertibility in Deep Neural Networks
… recent advances in machine learning involves neural networks with a large number of layers, often referred to as deep learning. In this dissertation, we study how to equip deep neural networks with two useful properties: invariance and invertibility. The first part of our work is focused on …
-
An Agent Based Model to Assess Crew Temporal Variability During U.S. Navy Shipboard Operations
… Discrete Event Simulation, Bayesian Belief Networks, Neural Networks, and a multitude of existing software applications to provide relevant assessments of human task performance and temporal variability. The objective of this research was to design and develop a novel Agent Based Modeling …
-
Tactile pattern recognition using neural networks.
… capture and recognition of tactile images using neural networks. Neural Networks utilizing the backpropagation technique are used to provide a general purpose recognition engine for several classes of pattern recognition problems. Examples of successful networks are presented with discussion of …
-
The effects of using problem knowledge in a neural network for image processing tasks : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science at Massey University, Palmerston North, New Zealand
… field of computational intelligence, is that of neural networks. Neural networks are networks of artificial neurons with a high degree of interconnectivity. The networks capture and accumulate knowledge as the pattern of weights in the interconnections between neurons. Neural networks are …
-
Augmented Neural Network Surrogate Models for Polynomial Chaos Expansions and Reduced Order Modeling
… surrogate modeling solution is with the usage of neural networks. Neural networks (NN) are known to generalize an approximation across a diverse dataset and minimize the solution along complex nonlinear boundaries. Additionally, these surrogate models can be found using only incomplete knowledge …
-
Large-Scale Optimization for Deep Neural Network Architecture: A Dynamical System Theory Perspective
Optimization of deep neural networks (DNNs) has been a driving force in the advancement of modern machine learning and artificial intelligence. Despite efforts to design DNN architectures that leverage domain-specific knowledge, the development of optimization algorithms for training these …
-
Neural networks for modeling and control of particle accelerators
… this dissertation focuses on approaches based on neural networks. Neural networks are particularly well-suited to modeling, control, and diagnostic analysis of nonlinear systems, as well as systems with large parameter spaces. They are also very appealing for their ability to process …
-
Transmitter Optimization Techniques for Physical Layer Security
… is one of the most critical issues in wireless networks as the signals transmitted through wireless medium are more vulnerable for interception. Although the existing conventional security techniques are proven to be safe, the broadcast nature of wireless communications introduces different …
-
Design and Implementation of Machine Learning Models and Algorithms for Flood, Drought and Frazil Prediction
… architecture that leverages Long Short Term Networks - neural networks to predict water height accurately in three different environmental scenarios, i.e., frazil, droughts and floods due to snow spring melt. A distinguishing feature of our approach is the incorporation of meteorological …
-
Application of neural networks to measurement of temperature sensor response time
<p>A neural network, implementing the backpropagation paradigm, has been developed to predict the time constants of resistance temperature detectors (RTDs) from loop current step response (LCSR) test transients. It eliminates the difficulties involved in the LCSR application: complicated …
-
NEURAL RETRIEVAL THROUGH ENTITIES AND TEXT UNDERSTANDING
… relevant documents. With the emergence of neural networks, Neural IR approaches utilize deep learning techniques to learn high-dimensional representations of documents and queries that go beyond term matching.On the other hand, with the development of symbolic knowledge graphs (KGs), the IR …
-
Turbines for flexible power plant operation
… developed utilising plant measurements, thermal networks, neural networks and simulation data.</p> <p>Validation cases and future developments are explored, highlighting the potential of the hybrid modelling concept. Demonstrated in the case of thermal analysis for flexible operation of power …
-
Learning Robust Tractable Models for Vision
… four desiderata, weaving together sum-product networks, neural networks, kernel machines, and symmetry group theory. First, we extend sum-product networks so that they can be trained discriminatively. This expands the space of SPN architectures and allows feature functions, making them a …
-
Resting-State Cerebral Perfusion Patterns: An Exploratory Factor Analysis of Single-Photon Emission Computed Tomography Clinical Data
Resting-state (RS) networks (neural regions demonstrating a temporal correlation when a person is not engaged in deliberate activity) are a new topic in neuroscience and neuropsychology, not gaining significant traction in the literature until 2005. Few studies have used single-photon emission …
-
A study of facial expressions using neural networks
… aims to explore that hypothesis further using Neural Networks. Neural Network analysis was carried out using Adaptive Resonance Theory 2, Competitive Learning, Learning Vector Quantization and Multi-Layer Perceptrons. These networks collectively facilitated both a linear and non-linear analysis …
Page 1 of 8