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 420 for “"edge devices"”.

  1. Slimmable neural networks for edge devices

    … to run neural networks within latency budget for edge devices remains unsolved. This thesis presents a new approach to train a single neural network executable at arbitrary widths for instant and adaptive accuracy-efficiency trade-offs at runtime. First a simple and general method is presented to …

    uiuc Repository record for Slimmable neural networks for edge devices (opens in a new tab)

  2. Trustable machine learning development for edge devices

    … (TinyML). Perante a atual tendência de edge computing, os criadores de modelos de ML têm demonstrado preocupação com a sua propriedade intelectual. A implementação de modelos em dispositivos não confiáveis pode expor algoritmos proprietários, através de engenharia reversa, ou comprometer …

    minho-thes Repository record for Trustable machine learning development for edge devices (opens in a new tab)

  3. On-demand Crowdsourced Federated Learning over Edge Devices

    … learning (ML) model over a number of distributed devices while keeping all their training data localized. Under these settings, the edge devices perform computations on their local data before sending the required updates to the central server to improve the global model. This approach has shown …

    dcu Download PDF for On-demand Crowdsourced Federated Learning over Edge Devices (opens in a new tab)

  4. Efficient Deployment of AI Applications on Edge Devices

    … applications on resource-constrained edge devices. We present a comprehensive research trajectory that follows two parallel growth curves: increasing model complexity (from convolutional neural networks to transformers to Mixture-of-Experts architectures) and expanding edge device …

    toronto-retro Repository record for Efficient Deployment of AI Applications on Edge Devices (opens in a new tab)

  5. MODEL OPTIMIZATION FOR VEHICLE RECOGNITION ON EDGE DEVICES

    … be supported. The emergence of lightweight edge devices with low power requirements and high processing power to run AI, however, has offered an avenue to deploy AI in remote areas. Thus, the focus shifts to the type of AI used in video surveillance systems. One approach is machine learning …

    nps Repository record for MODEL OPTIMIZATION FOR VEHICLE RECOGNITION ON EDGE DEVICES (opens in a new tab)

  6. Communication-efficient personalization in federated learning for edge devices

    … and a compact, shared adapter for knowledge transfer, augmented with selective pruning to balance local adaptation and global generalization for vision and language tasks. Then, we present a lightweight, convolution-based approach to time-series forecasting that pairs learnable …

    iastate Repository record for Communication-efficient personalization in federated learning for edge devices (opens in a new tab)

  7. Neural Network Reduction for Efficient Execution on Edge Devices

    … neural networks to be grown and trained within edge devices, Artificial Neurogenesis and Synaptic Input Consolidation.

    arizona-thes Repository record for Neural Network Reduction for Efficient Execution on Edge Devices (opens in a new tab)

  8. Accelerating Multi-target Visual Tracking on Smart Edge Devices

    … Despite the superior performance of cutting-edge object detectors, their extensive computational demands limit their real-time application on embedded devices that possess constrained processing capabilities. Hence, we aim to reduce the computational burdens of object detection while …

    mcmaster Repository record for Accelerating Multi-target Visual Tracking on Smart Edge Devices (opens in a new tab)

  9. Enabling Cybersecure and Resilient Smart Distribution Grid with Edge Devices

    … advanced communication infrastructure, digital devices, and robust computation and control capabilities. Grid-edge devices including distributed energy resources (DERs) like solar photovoltaics (PV), battery storage systems, and intelligent electric loads like electric vehicles and smart …

    wvu Repository record for Enabling Cybersecure and Resilient Smart Distribution Grid with Edge Devices (opens in a new tab)

  10. REAL-LIFE HEALTH APPLICATIONS OF WIRELESS SENSING USING EDGE DEVICES

    … (NLoS) scenarios. The growing availability of edge computing devices further enables real-time on-device data processing, making wireless sensing solutions highly suitable for in-home health monitoring and smart living applications. This dissertation investigates real-life health applications …

    vcu Repository record for REAL-LIFE HEALTH APPLICATIONS OF WIRELESS SENSING USING EDGE DEVICES (opens in a new tab)

  11. Spatiotemporal Analysis on Distributed Task Offloading in Extreme Edge Devices

    … Internet of Things (IoT), the number of smart devices connected to the Internet is exponentially increasing, resulting in large-scale data and inadequate resources, which has caused high congestion and slow response delay in legacy cloud computing models. Multi-access Edge Computing (MEC) is a …

    queens Repository record for Spatiotemporal Analysis on Distributed Task Offloading in Extreme Edge Devices (opens in a new tab)

  12. Squeeze and Excite Residual Capsule Network for Embedded Edge Devices

    During recent years, the field of computer vision has evolved rapidly. Convolutional Neural Networks (CNNs) have become the chosen default for implementing computer vision tasks. The popularity is based on how the CNNs have successfully performed the well-known computer vision tasks such as image …

    iupui Repository record for Squeeze and Excite Residual Capsule Network for Embedded Edge Devices (opens in a new tab)

  13. Enabling Multi-Task Neural Network Inference on Heterogeneous Edge Devices

    … networks are increasingly required to run on the devices that generate the data. If such a device must perform more than one task, the standard practice is deploying one model per task, which makes memory grow linearly with task count, which is unacceptable when the entire budget is kilobytes. …

    kennesaw Repository record for Enabling Multi-Task Neural Network Inference on Heterogeneous Edge Devices (opens in a new tab)

  14. Innovative decentralized decision-making enabling capability on mobile edge devices

    … equipment organically assigned to the edge users are unable to meet the ever increasing information exchange requirements. The computational and throughput capability in current fielded communication systems are unable to keep pace with the ever increasing bandwidth intensive …

    nps Repository record for Innovative decentralized decision-making enabling capability on mobile edge devices (opens in a new tab)

Page 1 of 21