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 29 for “"Generative neural network"”.
-
A Generative Neural Network for Discovering Near Optimaldynamic Inductive Power Transfer Systems
… method for dynamic IPT systems that utilize generative neural networks. Deep learning is applied to create a generator of near-optimal design alternatives from random noise. Two neural networks are employed in the approach. The first neural network is trained from multiple FEM results through …
-
Deep Generative Neural Network Models for Capturing Complex Patterns in Visual Data
… nor modify input samples. Unsupervised deep generative models have the potential to avoid these problems. However, the two dominant families of generative models, Generative Adversarial Networks (GAN)and Variational Autoencoders (VAE), each come with their characteristic problems. GAN-based …
-
Generative Neural Network Approach to Designing and Optimizing Dynamic Inductive Power Transfer Systems
… near-optimal designs, a machine-learning, Generative Neural Network (GNN) approach is presented for the rapid development of near-optimal DIPT systems. GNNs generate new examples from a trained neural network and have demonstrated remarkable power in creating novel graphic design images …
-
Generative Neural Network-Based Defense Methods Against Cyberattacks for Connected and Autonomous Vehicles
… for cyber threats. Recently, the emergence of generative neural networks (NNs) has unveiled a myriad of opportunities for complementing CAV applications, including generative NN-based cybersecurity measures to protect the CAVs in a transportation cyber-physical system (TCPS) from known and …
-
Two-way Multi-input Generative Neural Network for Anomaly Event Detection and Localization
… In this thesis, we propose a Two-way Multi-input Generative Neural Network (TMGNN), which is an unsupervised anomaly events detection and localization method based on Generative Adversarial Network (GAN). TMGNN is composed of two neural networks, an appearance generation neural network and a …
-
Investigating Semantic Properties of Images Generated from Natural Language Using Neural Networks
… attributes, properties, and potential uses of generative neural networks within the realm of encoding semantics. It works toward answering the questions of: If one uses generative neural networks to create a picture based on natural language, does the resultant picture encode the text's …
-
Bayesian inverse problems with neural generative priors
… We present a data-driven framework where a generative neural network in the form of a Wasserstein Generative Adversarial Network (WGAN) learns a realistic prior, decoupled from the inverse problem in consideration. The method is tested on a severely undersampled two dimensional MRI analogue. …
-
Aukštos energijos fizikos duomenų generavimas naudojant giliuosius neuroninius tinklus /
… high‐energy physics particles using artificial neural network methods. In high‐energy physics experiments (e.g. the CMS experiment at CERN), generating large volumes of such data often relies on Monte Carlo simulations that require very high computing resources. To reduce the computational cost …
-
Phase Retrieval Under a Generative Prior
… We sidestep this issue by enforcing a generative prior: the assumption that the signal is in the range of a generative neural network. By formulating an empirical risk minimization problem and directly optimizing over the domain of the generator, we show that the objective’s energy …
-
A Deep Hierarchical Variational Autoencoder for World Models in Complex Reinforcement Learning Environments
… model is a model-based RL approach that employs generative neural network models to learn a compressed spatial and temporal representation of the environment. This work explores world models and a simple single-layered RNN model to learn a simple policy based on the representations to solve tasks …
-
Generative compressed sensing with Fourier measurements
… and the signal structure is the range of a generative neural network (GNN). The problem of compressed sensing with GNNs has since been extensively analyzed when the measurement matrix and/or network weights follow a subgaussian distribution. In this thesis, we move beyond the subgaussian …
-
A sparsity-free compressed sensing theory with applications in generative model recovery
… set. We apply our results to the special case of generative priors, i.e. when x is close to the range of a Generative Neural Network (GNN) with ReLU activation functions. Also, if the GNN has random weights in the last layer, our theory allows a partial Fourier measurement matrix, thus taking the …
-
Integrating Perception, Prediction and Control for Adaptive Mobile Navigation
… is accomplished through the development of novel generative neural network architectures that enable map prediction that exceed the limitations of the sensor. Further, I extend the neural network architectures to predict multiple hypotheses and use the variance of the hypotheses as a measure of …
-
Big Data For Microorganisms: Computational Approaches Leveraging Large-Scale Microbial Transcriptomic Compendia
… signals of interest. In Chapter 2, we use a generative neural network to simulate gene expression compendia with varying amounts of technical variability and assess the ability to detect the underlying biological structure in the data after noise was added and then after batch correction was …
-
Neural waveform generation for source-filter vocoding in speech synthesis
… in statistical model based synthesis using neural networks, speech synthesis has reached an unprecedented level of naturalness and flexibility that will make possible many exciting future applications. A major contributor to the recent improvements has been the introduction of neural network …
-
Advanced Techniques For Prediction of Forest Above Ground Biomass Using Satellite Remote Sensing Data
… data. The second contribution presents a dynamic generative neural network architecture for modelling AGB using multi-sensor satellite RS data. It proposes a method to derive AGB-oriented features and provides a seamless multi-sensor feature fusion method for AGB prediction. The third contribution …
-
Improving Reinforcement Learning Techniques for Medical Decision Making
… states from observed clinical data. We use a generative neural network architecture that learns a direct mapping between distributions over clinical measurements at adjacent time points. We show that this model produces realistic patient trajectories and can be paired with on-policy RL to …
-
Metric Gaussian variational inference
… to use several, independently trained and deep neural networks to reason on complex tasks. Deep learning allows to capture abstract concepts by extracting them from large amounts of training data, which alleviates the necessity of an explicit mathematical formulation. Here a generative neural …
-
Finite Element Analysis of Reinforced Concrete Slab-Column Connections for Seismic Performance Investigation
… using numerical FEA. Consequently, a deep neural network was trained over the accumulated dataset and integrated into the OpenSees source code. For data augmentation, a generative neural network model of autoencoders known as Generative Adversarial Networks was constructed to generate …
-
Detecting Anomalies in Transaction Data
… To implicitly model numerical dependencies, Neural Arithmetic Logic Units have been proposed as neural architecture. In practice, however, these have stability and precision issues. Therefore, we first develop an improved neural network architecture, iNALU, which is designed to better model …
Page 1 of 2