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 23 for “"Fine-Tuning Strategies"”.

  1. Efficient Fine-Tuning Strategies for Federated Learning: Optimizing Model Performance Across Distributed Networks

    … strate its efficiency and combine it with full fine-tuning to produce stronger performance. Then, we introduce an adapted zeroth-order method capable of bringing a model to convergence with a mini- mal per-round compute budget while reducing the memory burden for clients during training down to …

    concordia Download PDF for Efficient Fine-Tuning Strategies for Federated Learning: Optimizing Model Performance Across Distributed Networks (opens in a new tab)

  2. A comparative analysis of large language models on medical datasets : performance evaluation and fine-tuning strategies

    … regarding domain-specific benchmarks and fine-tuning with specialized datasets. This study addresses this gap by investigating the role of KD in enhancing LLM performance within the medical domain, where accuracy and contextual understanding are crucial. A dual-track approach is adopted: …

    texas Repository record for A comparative analysis of large language models on medical datasets : performance evaluation and fine-tuning strategies (opens in a new tab)

  3. Self-Supervised Vision Transformers for Steel Surface Defect Detection - An Empirical Investigation of Fine-Tuning Strategies and Data Efficiency

    … methods under different conditions, including fine-tuning vs linear probing, ImageNet initialization vs training from scratch and varying amounts of labeled data. A comprehensive experimental setup is used to assess both overall performance and label efficiency and results are compared to a …

    chalmers Repository record for Self-Supervised Vision Transformers for Steel Surface Defect Detection - An Empirical Investigation of Fine-Tuning Strategies and Data Efficiency (opens in a new tab)

  4. Region-of-Interest Detection for the Neonatal Intensive Care Unit

    … from adult data under different pretraining and fine-tuning strategies. Lastly, this thesis demonstrates that it is possible to estimate full pose from neonates even when the patient is fully occluded, using a combination of pressure and depth imagery.

    carleton Repository record for Region-of-Interest Detection for the Neonatal Intensive Care Unit (opens in a new tab)

  5. EFFORTS TOWARD TRUSTWORTHY MACHINE LEARNING: MITIGATING OVERCONFIDENCE, HALLUCINATION, AND MODALITY BIAS

    … challenges through post-hoc methods and targeted fine-tuning strategies. First, we mitigate overconfidence in discriminative models by introducing a neighborhood agreement metric that leverages foundation model representations, offering more reliable confidence estimates than softmax scores. We …

    nus Repository record for EFFORTS TOWARD TRUSTWORTHY MACHINE LEARNING: MITIGATING OVERCONFIDENCE, HALLUCINATION, AND MODALITY BIAS (opens in a new tab) Download file for EFFORTS TOWARD TRUSTWORTHY MACHINE LEARNING: MITIGATING OVERCONFIDENCE, HALLUCINATION, AND MODALITY BIAS (opens in a new tab)

  6. Analyzing Icelandic conversation using State-of-the-Art ASR models

    This thesis investigates the performance and fine-tuning of transformer-based Automatic Speech Recognition (ASR) systems applied to Icelandic conversational speech, with a primary focus on OpenAI’s Whisper model and a secondary fo- cus on Meta’s Wav2Vec 2.0. The study uses the Spjallrómur dataset, …

    reykjavik Repository record for Analyzing Icelandic conversation using State-of-the-Art ASR models (opens in a new tab)

  7. Harmonizing Divergence in Computational Discourse Analysis

    … IDRR. The thesis further explores prompting strategies using recent large language models and shows that fine-tuning strategies still perform better in this task. Together, these contributions advance the goal of harmonizing divergence in computational discourse analysis, offering more …

    concordia Download PDF for Harmonizing Divergence in Computational Discourse Analysis (opens in a new tab)

  8. Exploration in Personalized Federated Learning under Heterogeneous Multi-modal Environments

    … How can I design more effective personalization strategies to mitigate the adverse effects of non-IID data distributions? (2) Personalization for Missing Modality in Multimodal FL: How can I address the problem of missing modalities in multimodal federated settings without relying on auxiliary …

    adelaide Repository record for Exploration in Personalized Federated Learning under Heterogeneous Multi-modal Environments (opens in a new tab)

  9. Toward Transformer-based Large Energy Models for Smart Energy Management

    … architectures, utilizing both zero-shot and fine-tuning strategies, with data from 1,014 buildings. The results, evaluated across three prediction horizons (24, 72, and 168 hours), confirm that GEMs significantly outperform Transformer-based in-situ (i.e., building-specific) models. …

    vt Repository record for Toward Transformer-based Large Energy Models for Smart Energy Management (opens in a new tab)

  10. On Bed Posture Recognition Using Deep Learning With Pressure Sensors

    … approaches to get over these restrictions, then fine-tuned it using the following deep learning architectures for bed posture recognition: ResNet-50, EfficientNet-B0, MobileNetV2, EfficientNet-B4, and ResNet-101. Our approach involves pressure sensor-based bed posture detection entails …

    csusb Repository record for On Bed Posture Recognition Using Deep Learning With Pressure Sensors (opens in a new tab)

  11. Sequence-to-Sequence Automatic Sentence Simplification: Development & Evaluation

    … the research investigates the potential of fine-tuning pre-trained Large Language Models (LLMs) for simplifying complex sentences. It assesses the integration of LLMs into Seq2Seq models and their adaptation to the simplification task, aiming to leverage the benefits of pre-trained language …

    whiterose Download PDF for Sequence-to-Sequence Automatic Sentence Simplification: Development & Evaluation (opens in a new tab)

  12. Prior knowledge-driven model pre-training and fine-tuning for ophthalmic image analysis

    … lesions, and the inefficiency of conventional fine-tuning strategies for large pre-trained models (LPMs). This thesis addresses these challenges by developing and evaluating novel pre-training and fine-tuning frameworks tailored for ophthalmic imaging. We first establish a strong and …

    ubc Repository record for Prior knowledge-driven model pre-training and fine-tuning for ophthalmic image analysis (opens in a new tab) Download PDF for Prior knowledge-driven model pre-training and fine-tuning for ophthalmic image analysis (opens in a new tab)

  13. Efficient Multimodal Foundation Model Tuning For Hallucination Mitigation

    … from fixed learning (static, offline fine-tuning) to adaptive, feedback-driven lifelong learning. By incorporating test-time adaptation, it seeks to enable multimodal foundation models to evolve through interaction with real data. In this process, an evaluator assesses the overall …

    uab Repository record for Efficient Multimodal Foundation Model Tuning For Hallucination Mitigation (opens in a new tab)

  14. Privacy-Preserving AI for Mental Wellbeing Monitoring: From Passive Sensing to Online Engagement, through a User-Centred Lens

    … retrieval-augmented<br/>generation, and fine-tuning strategies across model scales, and showing that compact fine-tuned<br/>models can achieve strong accuracy while remaining efficient enough to run directly on personal<br/>devices. This makes it possible to provide responsive, real-time …

    bristol Repository record for Privacy-Preserving AI for Mental Wellbeing Monitoring: From Passive Sensing to Online Engagement, through a User-Centred Lens (opens in a new tab) Download PDF for Privacy-Preserving AI for Mental Wellbeing Monitoring: From Passive Sensing to Online Engagement, through a User-Centred Lens (opens in a new tab)

  15. Uncertainty-Aware and Data-Efficient Fine-Tuning and Application of Foundation Models

    … (ELREA), designed for date-efficient multi-task fine-tuning, which clusters training instructions based on gradient directions and applies task-specific Low-Rank Adaptation (LoRA) experts through ensemble techniques. ELREA mitigates task interference, promoting better generalization and parameter …

    gatech Repository record for Uncertainty-Aware and Data-Efficient Fine-Tuning and Application of Foundation Models (opens in a new tab)

  16. A Multifaceted Analysis of Model Generalization in Challenging Environments

    … architectures, training distributions, and fine-tuning strategies in Chapter 3. Beyond overall accuracy, the analysis examines robustness with respect to specific visual factors, out-of-distribution conditions, and the interaction between vision and language encoders. It further incorporates …

    anu Repository record for A Multifaceted Analysis of Model Generalization in Challenging Environments (opens in a new tab)

  17. Anthrogames

    … social-media datasets and optimized via specific fine-tuning strategies to ensure temporal robustness and cross-lingual generalization. Fifth, and independently of the safeguarding layer, the thesis implements and evaluates the continuous pretraining of a mid-scale multilingual large language …

    fu-berlin Repository record for Anthrogames (opens in a new tab)

  18. Enhancing language models for telecom networks using retrieval-augmented generation: A pipeline for telecom-specific QA system

    … as the interpretation of technical standards defined by organizations such as Third Generation Partnership Project (3GPP) standards, industry-specific jargon, and the need for precise technical answers necessitate specialized models and effective telecom question-answer systems. In this thesis, …

    regina Repository record for Enhancing language models for telecom networks using retrieval-augmented generation: A pipeline for telecom-specific QA system (opens in a new tab)

  19. AI for Medical Imaging: Foundation Models, 2D-to-3D Reconstruction, and Clinical Applications

    … problem.</p><p>This dissertation explores strategies for developing and applying medical image segmentation algorithms, with a focus on adapting vision foundation models to the medical domain and integrating segmentation into downstream clinical and technical applications.</p><p>In Chapter …

    duke Repository record for AI for Medical Imaging: Foundation Models, 2D-to-3D Reconstruction, and Clinical Applications (opens in a new tab)

  20. Robustness under distribution shifts in computer vision

    … two distribution shifts and propose mitigation strategies to improve their robustness to the shifts. Prior Shifts: improving recall without sacrificing precision. Prior shifts can arise when i) the training class distribution does not match the true (test) class distribution due to the inherent …

    gatech Repository record for Robustness under distribution shifts in computer vision (opens in a new tab)

Page 1 of 2