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 11 of 11 for “"Training Stability"”.
-
Reducing Global Memory Accesses in DNN Training using Structured Weight Masking
Training large deep neural networks (DNNs) is often constrained by memory bandwidth, with frequent global memory accesses representing a significant performance bottleneck. This thesis investigates the potential of dynamic structured weight masking to alleviate this bottleneck during training, …
-
Natural video synthesis with Generative Adversarial Networks
… experiments show that model inflation improves training speed, training stability, and output video quality. The segmentation-to-video task is that of turning an input image segmentation mask into an output video matching that segmentation. A GAN model was created to perform this task, and its …
-
Hierarchical reinforcement learning for adaptive and autonomous decision-making in robotics
… Second we introduce a confidence-based training process for the hierarchical controller which improves training stability and convergence times. These algorithmic contributions were evaluated using our development pipeline.
-
From data to model behaviour: A causal and empirical analysis of how data shapes the behaviour of language models
… are shaped not only by their architectures or training algorithms, but fundamentally by their training data---what examples they see, how those examples are represented, when they encounter them, and how much influence individual examples (or batches of examples) exert. Despite the critical …
-
Understanding the mechanism of pretraining stabilization heuristics: A variance-oriented perspective
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Understanding the mechanism of pretraining stabilization heuristics: A variance-oriented perspective
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
G A N mask R-CNN : instance semantic segmentation benefits from generative adversarial networks
… matching one. We discuss how we utilize the GANs training stability regiments in practice to make this concept works. We show this GANs framework performs better than the original Mask R-CNN. Furthermore, we show the results give crisper boundaries - a traditional challenge of ConvNets where there …
-
Guiding Deep Probabilistic Models
… part of the thesis, we develop novel stable training objectives for Generative Adversarial Networks (GANs). We show that under standard unary-discriminator objectives, most of the valid solutions, where the learned distribution is aligned with the target, are unstable. We propose training …
-
Interpretable Knowledge Transfer in Communicative Neural-based Swarm-Guidance Agents
… algorithm, the Extended C-Net, leverages the training data to learn the association between the NN's nodes at the final hidden layer and the outputs and then uses recursive back-projections to derive the rules regulating input-output relationships. Performance is assessed using three measures: …
-
Theoretical Understanding of Neural Network Optimization Landscape and Self-Supervised Representation Learning
… which learns the representations during pre-training and applies learned representations in downstream tasks, has become the dominant approach for representation learning in recent years. However, theoretical understanding of self-supervised representation learning is scarce. Two main …
-
GNN-Enhanced Hierarchical Federated Learning in Device-to-Device Networks
… paradigm for collaborative model training across distributed devices without sharing raw data, yet conventional FL architectures suffer from high communication overhead and poor scalability. Device-to-device (D2D) communication enables devices to exchange model updates directly and …