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 53 for “"Convolutional Networks"”.
-
Dynamic Spatio-Temporal Graph Convolutional Networks
… with changing graph structure. DST-GCN employs a convolutional architecture to learn spatio-temporal relationships that provide strong generalization and attractive computational efficiency. We provide empirical results for several datasets from different domains that demonstrate the gains …
-
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) …
-
Machine learning of image analysis with convolutional networks and topological constraints
… from previous work. The first is a focus on convolutional networks, a machine learning strategy that operates directly on an input image with no use of hand-designed features and employs many thousands of free parameters that are learned from data. Previous work in low-level vision has been …
-
An Empirical and Theoretical Analysis of the Role of Depth in Convolutional Neural Networks
While over-parameterized neural networks are capable of perfectly fitting (interpolating) training data, these networks often perform well on test data, thereby contradicting classical learning theory. Recent work provided an explanation for this phenomenon by introducing the double descent curve, …
-
Leveraging Basis Alignment to create a Generalized Multi-Relational Graph Convolution Network in the Federated Setting
… state-of-the-art Knowledge Embedding Based Graph Convolutional Network (KE-GCN) [51]. KEGCN was chosen for it’s unification of multiple graph convolutional networks and it’s ability to provide as much flexibility as possible for clients. As a result, my federated protocol, Fed-KE-GCN, is focused …
-
Characterizing Autism and Schizophrenia Using PRISM and Deep Learning
… to multiplexed immunofluorescence data. Deep convolutional networks are developed and applied to analyze PRISM images of neurons treated with gene knockdown treatments corresponding to genes associated with autism and schizophrenia. Similarities and differences between normal-type and …
-
Generalized flow-based variational autoencoder networks for anomaly detection in multivariate time series
… compared to prior research, of flows and convolutional networks for anomaly detection by improving popular metrics like the F1-score.
-
Personalized machine learning for facial expression analysis
… I investigated the personalization of deep convolutional networks for facial expression analysis. While prior work focused on population-based ("one-size-fits-all") models for prediction of affective states (valence/arousal), I constructed personalized versions of these models to improve …
-
Commonsense for Zero-Shot Natural Language Video Localization
… enhancement module. Our approach employs Graph Convolutional Networks (GCN) to encode commonsense information extracted from a knowledge graph, conditioned on the video, and cross-attention mechanisms to enhance the encoded video and pseudo-query vectors prior to localization. Through empirical …
-
Graph structures, random walks, and all that : learning graphs with jumping knowledge networks
… of drugs, community detection in social networks, and modeling interactions in physical systems. Recent deep learning approaches for graph representation learning, namely Graph Neural Networks (GNNs), follow a neighborhood aggregation procedure, where the representation vector of a node …
-
Evaluating robustness of neural networks with mixed integer programming
Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, neural networks can be fooled by adversarial examples -- slightly perturbed inputs that are misclassified with high confidence. Verification of networks enables us to gauge their vulnerability …
-
Random Sequential Encoders for Private Data Release in NLP
… task. In computer vision, lightweight random convolutional networks have shown potential to be an encoder that balances privacy and utility. This thesis takes a novel exploration of random sequential encoders - (1) random recurrent neural networks and (2) random long short-term memory networks …
-
Protein Function Prediction Using Graph Convolutional Network
… protein language models (PLMs) and graph convolutional networks (GCNs), addressing the limitations of traditional methods that rely heavily on sequence similarity. The proposed model leverages diverse protein features, including sequences, protein-protein interaction (PPI) networks, and …
-
The invariance hypothesis and the ventral stream
… idea. A recent general theory of hierarchical networks for invariant recognition [1] describes many modern convolutional networks as special cases, and also implies the existence of a wider class of algorithms, which we are only now beginning to explore. Our version of the invariance hypothesis …
-
A Multimodal Graph Convolutional Approach to Predict Genes Associated with Rare Genetic Diseases
… genes, and develop an approach based on graph convolutional networks. We show how our model design considerations impact prediction performance. We demonstrate that our approach outperforms simpler graph machine learning and traditional machine learning approaches, as well as a competitive …
-
Learning multiple solutions to computer vision problems
… question answering [22, 23, 24, 25, 26] etc. Convolutional neural networks [27, 28] and/or Recurrent Neural Networks [29] trained to regress to a single value or classify to a single class label are the workhorse of most of these methods. However, many computer vision problems are ambiguous …
-
Graph Learning and Optimization for Irregular-Structured Signal Processing
… costs for deep learning models (e.g, graph convolutional networks (GCNs)). Together, these contributions provide a flexible and computationally efficient approach to GSP in dynamic and large-scale graph settings.
-
MEng Thesis: Incorporating Structured Commonsense into Language Models
… text. We harness the power of relational graph convolutional networks (RGCNs) to encode meaningful commonsense information from graphs and introduce 3 simple methods to inject this knowledge to improve contextual language representations from transformer-based language models. We show that the …
-
Accelerating Conceptual Design Analysis of Marine Vehicles through Deep Learning
… of cases considered. Machine learning through convolutional networks is employed to discover the relationship between vehicle geometries and their associated flow fields with two distinct deep-learning networks. The first network directly maps explicitly-specified geometric design parameters to …
-
The Deep Rendering Model: Bridging Theory and Practice in Deep Learning
… to a discriminative one, we can recover deep convolutional neural networks (DCNs) as well as its variants including the deep residual networks (ResNet) and the densely connected convolutional networks (DenseNet), providing insights into their successes and shortcomings as well as a principled …
Page 1 of 3