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 57 for “"Transformer networks"”.
-
Optical Temperature Monitoring of Electrical Power Transformer Networks
… network model designed to monitor temperature of transformers at multiple substations from one central location. Fiber Bragg Grating (FBG) has been used as the optical sensing element for transformer temperature monitoring. Suitable FBG parameters and specifications have been investigated and …
-
Detection in Aerial Images Using Spatial Transformer Networks
… in aerial images. Both systems leverage Spatial Transformer Networks (STN) that identify the coordinate transformation for their localization capabilities. The first approach is based on a semisupervised approach which learns to locate changes within a difference image. The second is a …
-
Systematic Exploration of Power-Augmented Feedforward Layers in Transformer Networks
… architecture of deep learning neural networks, consisting of fully-connected layers organized in a hierarchical structure. While activation functions between layers introduce non-linearity to the overall network, the fundamental computation within each layer remains strictly linear, …
-
Transformative Diagnostics: Applying Transformer Networks and Semantic Guidance to Whole Slide Images
… leveraging advanced segmentation techniques, transformer-based models, and a novel Semantics-Aware Attention Guidance (SAG) framework.The initial focus of the research is on enhancing the detection and segmentation of diag- nostically significant structures within WSIs. The introduction of …
-
Transformer Networks for Smart Cities: Framework and Application to Makassar Smart Garden Alleys
… S&CC problem sets concurrently. Attention-based Transformer networks are of particular interest given their success across diverse fields of natural language processing (NLP), computer vision, time-series regression, and multi-modal data fusion in recent years. This begs the question whether …
-
On Studying Transformer Networks for Volume-to-Surface Registration of Inhomogeneous Soft Bodies for Liver Laparoscopy
… In particular, we investigate the use of vision transformer attention blocks within a U-Net structure to improve the prediction of a displacement field between the preand intraoperative surfaces. We also investigate the robustness of these networks by creating novel training data with imperfect …
-
Efficient Scopeformer: Towards Scalable and Rich Feature Extraction for Intracranial Hemorrhage Detection using Hybrid Convolution and Vision Transformer Networks
… in medical imaging. Convolutional neural networks (CNNs) are the go-to architecture for computer vision problems, but they have limitations in mapping long-term dependencies within images. To address these limitations, the study explores the use of techniques such as global average pooling …
-
Generative methods for image synthesis with applications to medical imaging
… use of a hybrid model of generative adversarial networks (GANs) and transformer networks for image synthesis. We propose a method that combines GANs with transformer networks to address the translation and super-resolution of medical images. We also present a model for inpainting of images. …
-
Automatic target recognition with convolutional neural networks.
… to solve the ATR task using Convolutional Neural Networks (CNN). We present three learning approaches using WideResNet-28-2\cite{wrn} as a backbone CNN. The first method uses random initialization of the network weights. The second method explores transfer learning. Finally, the third approach …
-
Semantic segmentation architecture based on Atrous Spatial Pyramid Pooling and convolutional based attention module for mapping of burned areas in satellite images
… successful in natural language processing tasks, transformer networks have recently been adapted for computer vision applications. These networks utilize self-attention layers, which are crucial to their design. SegFormer is a transformer-based model for semantic segmentation that has shown …
-
Resource-Efficient Machine Learning via Count-Sketches and Locality-Sensitive Hashing (LSH)
… to handle these datasets. (e.g., large-scale transformer networks for language modeling). The increase in the number of input features, model size, and output classification space is straining our limited computational resources. Given vast amounts of data and limited computational resources, …
-
Stichinių nelaimių žalos vertinimas iš nuotraukų /
… techniques such as convolutional neural networks and transformer networks to analyse optical and SAR imagery through feature fusion. The models developed in the work show that feature‑level synthesis is superior to image aggregation and that the developed convolutional network approach …
-
ON SYMMETRIC STRUCTURES IN MACHINE LEARNING: NEURAL NETWORKS, GAMES, AND GRAPHICAL MODELS
… key architectures such as convolutional and transformer networks. Despite their empirical success, their theoretical roles remain underexplored. This thesis investigates the theoretical impact of symmetry and invariance across neural networks, game theory, and graphical models. We first …
-
Parallelizing Legendre Memory Unit Training
… original LMU and a variety of published LSTM and transformer networks across seven benchmarks. For instance, our LMU sets a new state-of-the-art result on psMNIST, and uses half the parameters while outperforming DistilBERT and LSTM models on IMDB sentiment analysis.
-
Mažos skiriamosios gebos taškinės grafikos paveikslų gavimas pasitelkiant neuroninius tinklus /
… this work attempt was made to review how GAN and transformer works, a few of their modifications, to create a model capable of generating from high quality images pixelart. While the experiments was is progress the model was being made, by using generator and discriminator principles, to create a …
-
Person Re-identification in Images and Videos
… person re-identification approach with Spatial Transformer Networks. Most previous deep learning based approaches use whole image features to compute the similarity between images. This is not very intuitive since not all the regions in an image contain information about the person identity. …
-
Tree-Based Graph Neural Networks for Natural Language Inference: From Structure-Only to Hybrid Architectures
Large transformer models achieve strong performance on natural language understanding tasks but require hundreds of millions of parameters and extensive pretraining. This thesis investigates whether graph neural networks operating on dependency parse trees can provide more parameter-efficient …
-
Localizing Objects with Weak Supervision
… the class activation mechanism of CNN networks and find that object activation can be greatly improved without retraining the baseline model. We present an inference-only solution named class conditional inference module which reveals the classification network's hidden object …
-
Duplicate bug report detection using siamese bert networks /
… techniques by either using recurrent neural networks with LSTM layers or convolutional neural networks. However, recent breakthroughs in natural language processing with an introduction of Transformer networks and specifically BERT Deep Bidirectional Transformers suggest novel approaches for …
Page 1 of 3