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"”.

  1. 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, …

    heid-thes Repository record for Reducing Global Memory Accesses in DNN Training using Structured Weight Masking (opens in a new tab)

  2. 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 …

    mit Repository record for Natural video synthesis with Generative Adversarial Networks (opens in a new tab)

  3. 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.

    uiuc Repository record for Hierarchical reinforcement learning for adaptive and autonomous decision-making in robotics (opens in a new tab)

  4. 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 …

    cambridge Repository record for From data to model behaviour: A causal and empirical analysis of how data shapes the behaviour of language models (opens in a new tab)

  5. 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

    uiuc Repository record for Understanding the mechanism of pretraining stabilization heuristics: A variance-oriented perspective (opens in a new tab)

  6. 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

    uiuc Repository record for Understanding the mechanism of pretraining stabilization heuristics: A variance-oriented perspective (opens in a new tab)

  7. 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 …

    mit Repository record for G A N mask R-CNN : instance semantic segmentation benefits from generative adversarial networks (opens in a new tab)

  8. 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

    mit Repository record for Guiding Deep Probabilistic Models (opens in a new tab)

  9. 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: …

    unsw Repository record for Interpretable Knowledge Transfer in Communicative Neural-based Swarm-Guidance Agents (opens in a new tab)

  10. 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 …

    duke Repository record for Theoretical Understanding of Neural Network Optimization Landscape and Self-Supervised Representation Learning (opens in a new tab)

  11. 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 …

    exeter