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 297 for “"Convolutional Networks"”.
-
Convolutional networks to relate images
Within recent years, convolutional neural networks have experienced a come back and are currently dominating the field of computer vision.<br>In contrast to previously used methods, they allow for full data-based end-to-end training without the need to manually engineer features.<br>On the …
-
Deep convolutional networks without backpropagation
This thesis attempts to develop networks trained without gradient descent or backpropagation designed specifically for classification tasks. The emergence of issues with gradient-based neural networks, such as long training time, vanishing or exploding gradients and high computational costs, has …
-
Dense convolutional networks for efficient video analysis
In the past few years, artificial intelligence has ushered in the third climax, which is due to the improvement of hardware computing power, so that deep learning algorithm can be applied on a large scale. Before the large-scale use of deep learning, image feature engineering is more dependent on …
-
Efficient Fully-Convolutional Networks for Image Perception
… architecture search is widely applied to design networks to outperform manually designed architectures. However, it is not trivial to be directly applied to challenging perception tasks such as object detection since previous methods often rely on manually designed complex operations such as RoI …
-
Social Media Analytics with Graph Convolutional Networks
… social relationships established on social networks can be leveraged to market products or make recommendations. However, the open nature of online social media provides a favorable environment for malicious users to spread incorrect information, either for financial gains or to increase …
-
Multimodal Emotion Recognition Using Temporal Convolutional Networks
… Our results demonstrate that temporal convolutional networks outperform long short-term memory models in multimodal emotion prediction. Overall, our research contributes to advancing the field of affective computing by developing more accurate and comprehensive methods for modeling and …
-
Protein interface prediction using graph convolutional networks
… a revolution of sorts with the emergence of convolutional neural networks as the leading method of choice for a wide swath of tasks. Enabled by large quantities of data and the increasing power and availability of computing resources, convolutional neural networks efficiently detect patterns …
-
Traffic flow prediction with graph convolutional networks
… network. We study the use of graph convolutional networks for traffic speed prediction. Different models are investigated utilising internationally benchmarked data before the most promising approach (Graph WaveNet) is applied to a new database of South African road network data. …
-
Efficient Fully Convolutional Networks for Dense Prediction Tasks
… labeling is required in such tasks. Deep neural networks have been the dominant solution since the invention of fully-convolutional neural networks (FCNs). Well-designed complicated network structures achieve state-of-the-art performance on benchmark datasets, but often with a high computational …
-
Two-Stream Convolutional Networks for Dynamic Texture Synthesis
… synthesis. The model is based on pre-trained convolutional networks (ConvNets) that target two independent tasks: (i) object recognition, and (ii) optical flow regression. Given an input dynamic texture, statistics of filter responses from the object recognition and optical flow ConvNets …
-
Deep Convolutional Networks without Learning the Classifier Layer
Deep convolutional neural networks (CNNs) are effective and popularly used in a wide variety of computer vision tasks, especially in image classification. Conventionally, they consist of a series of convolutional and pooling layers followed by one or more fully connected (FC) layers to produce the …
-
Joint spatial and layer attention for convolutional networks
… that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., “what” feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., “where”) to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) …
-
Speech Emotion Recognition in Conversations Using Graph Convolutional Networks
… graphs that are used to train a graph convolutional network to perform SERC. We empirically evaluate the effectiveness of SERC-GCN on two benchmark dataset; IEMOCAP and MELD. Results show that SERC-GCN outperforms existing baseline approaches on these datasets.
-
Convolutional Networks for Segmentation and Detection of Agricultural Mushrooms
… the first experiments we found that a standard Convolutional Neural Network was able to achieve an 87.5% average precision rating while a Fully Convolutional Network was able to achieve a 88.9% average precision rating in mushroom segmentation. In the second set of experiments, a Region-based …
-
Quality assessment of protein structures using graph convolutional networks
… In this work we describe Qε, a graph convolutional network that utilizes a minimal set of atom and residue features as input to predict the global distance test total score (GDTTS) and local distance difference test score (lDDT) of a decoy. To improve the model's performance, we …
-
Pose Estimation and Object Detection using Deep Convolutional Networks
… specifically, we introduce a higher-order graph convolutional framework with initial residual connections for 3D-to-2D pose estimation. The proposed approach is derived from implicit fairing on graphs using a scale-dependent graph Laplacian filtering scheme. Using multi-hop neighborhoods for node …
-
Unsupervised representational learning of hierarchical graphs with graph convolutional networks.
Interpretation of functional genomic data attempts to correlate gene and protein expression with phenotype. While direct analysis of gene relationships associated with phenotype manifestation provides reasonable correlations, their use for direct assessment often fails to capture numerous complex …
-
Applying graph convolutional networks for community detection: quantifying node influence /
This thesis extends a Graph Convolutional Network (GCN) implementation for community detection with three additions, all aimed at figuring out which nodes the model's decisions actually depend on. The first is a switch to structural features, which lets the same trained model run on graphs of any …
Page 1 of 15