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 9 of 9 for “"Generative Replay"”.

  1. Multi-Label Lifelong Machine Learning Using Deep Generative Replay

    … we identified, we introduced Multi-label Deep Generative Replay (MLDGR), a framework for learning from multi-label image datasets across a sequence of tasks with minimal forgetting. As an initial task, the MLDGR approach assigns multiple labels to images. This is achieved by utilizing a …

    ottawa-retro Repository record for Multi-Label Lifelong Machine Learning Using Deep Generative Replay (opens in a new tab)

  2. Class Incremental Learning in Deep Neural Networks

    … In this thesis, we propose an Incremental Generative Replay Embedding (IGRE) framework which employs a conditional generator for generative replay at the image embedding level, thus combining the superior performance of replay and reducing the memory complexities for replay at the same …

    waterloo Repository record for Class Incremental Learning in Deep Neural Networks (opens in a new tab)

  3. Tęstinio mokymosi taikymas kenkimo programų klasifikacijai naudojant giliuosius neuroninius tinklus /

    … of elastic weight consolidation, experience replay, generative replay, and a combination of elastic weight consolidation and generative replay on the stability-plasticity balance of a deep neural network applied to malware classification. For the experiments, a binary file dataset was …

    vilnius Repository record for Tęstinio mokymosi taikymas kenkimo programų klasifikacijai naudojant giliuosius neuroninius tinklus / (opens in a new tab)

  4. Training deep generative models via lifelong learning

    … limited to the classification task, and lifelong generative modelling remains a new stage. In this PhD thesis, our research goal mainly focuses on training deep generative models in the context of lifelong learning. The advantage of our research topic over general continual learning is that we can …

    whiterose Download PDF for Training deep generative models via lifelong learning (opens in a new tab)

  5. Deep generative similarity-weighted interleaved learning

    … a phenomenon termed catastrophic forgetting. Replay-based methods are currently the most effective defense against catastrophic forgetting in class-incremental image classification, yet naïve rehearsal raises storage and privacy concerns and often wastes computation on low-risk memories. This …

    texas Repository record for Deep generative similarity-weighted interleaved learning (opens in a new tab)

  6. Large Language Models, Prompting, and Synthetic Data Generation for Continual Named Entity Recognition

    … NER models. One way to achieve this is to use generative large-language models to create synthetic data. This work focuses on building the foundation for a generative replay approach. We aim to determine the efficacy of using Open AI's GPT-4 model to generate synthetic data to supplement the …

    vcu Repository record for Large Language Models, Prompting, and Synthetic Data Generation for Continual Named Entity Recognition (opens in a new tab)

  7. Reducing Catastrophic Forgetting in Self-Organizing Maps

    … its memory retention -- new decay functions and generative resampling schemes to facilitate generative replay in the model. We perform extensive experiments using split-MNIST with these approaches, demonstrating that the c-SOM significantly improves over the classical SOM. Additionally, we come …

    rit Repository record for Reducing Catastrophic Forgetting in Self-Organizing Maps (opens in a new tab)

  8. Adaptive and Responsible Machine Learning: From Incremental Learning to Unlearning and Safe Generation

    … using stored class centroids. In addition, a generative replay mechanism reusing a previously trained model synthesizes representative samples of past tasks. A knowledge distillation formulation operating on embedding clusters is further developed to preserve intra-class and inter-class …

    queens Repository record for Adaptive and Responsible Machine Learning: From Incremental Learning to Unlearning and Safe Generation (opens in a new tab)

  9. Robust Semantic Segmentation for Seismic Salt Interpretation under Data Variability and Continual Learning

    … work, we introduce StyleAdapt, a style-guided generative replay framework that eliminates the need to retain historical datasets by synthesizing representative replay samples using a compact Style Memory Bank. By preserving domain-specific appearance characteristics through learned style …

    houston Repository record for Robust Semantic Segmentation for Seismic Salt Interpretation under Data Variability and Continual Learning (opens in a new tab) Embargoed until 2028-08-01