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 3 of 3 for “"non-contrastive SSL"”.

  1. Manifold-Aware Regularization for Self-Supervised Representation Learning

    Self-supervised learning (SSL) has emerged as a dominant paradigm for representation learning, yet much of its recent progress has been guided by empirical heuristics rather than unifying theoretical principles. This thesis advances the understanding of SSL by framing representation learning as a …

    waterloo Repository record for Manifold-Aware Regularization for Self-Supervised Representation Learning (opens in a new tab)

  2. Self-Supervised Representation Learning for Time Series Classification

    … has focused on self-supervised learning (SSL) to learn meaningful representations from unlabelled data. SSL achieves this by training neural network models on pretext tasks designed to encourage the learning of generalisable features that transfer well to downstream tasks. Most SSL …

    unsw Repository record for Self-Supervised Representation Learning for Time Series Classification (opens in a new tab)

  3. Approaches and Techniques to Enhance Efficiency and Performance of Non-Contrastive Self-Supervised Learning Methods

    Self-supervised learning (SSL) methods have gained considerable attention in recent years due to their ability to learn useful representations of data without relying on labels during training. These methods have revolutionized research across various domains, including Natural Language Processing, …

    waterloo Repository record for Approaches and Techniques to Enhance Efficiency and Performance of Non-Contrastive Self-Supervised Learning Methods (opens in a new tab)