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 6 of 6 for “"Adaptive Inference"”.

  1. Theoretical guarantees and complexity reduction in information planning

    … of belief propagation that is suitable for adaptive inference settings. In the first part, we present conditions under which open-loop is equivalent to closed-loop information planning. Furthermore, we provide bounds on the greedy performance for submodular non-monotone functions. We also …

    mit Repository record for Theoretical guarantees and complexity reduction in information planning (opens in a new tab)

  2. A Unified Framework for Distributed and Resource-Aware Plant Disease Detection Using Federated and Adaptive Hybrid Deep Learning

    … While LR models enable efficient real-time inference, they often lack the representational capacity required to accurately detect complex disease patterns. In contrast, high-resource (HR) models achieve superior detection performance due to their deep architectures but are computationally …

    usm Repository record for A Unified Framework for Distributed and Resource-Aware Plant Disease Detection Using Federated and Adaptive Hybrid Deep Learning (opens in a new tab)

  3. Resource efficient distributed inference of deep neural networks for Edge AI

    … framework for resource-efficient distributed inference of DNNs in Edge AI, built upon three tightly coupled research objectives: asynchronous split inference, adaptive batching for resource efficiency, and tensor compression at the client–server boundary. First, the study introduces an …

    umkc Repository record for Resource efficient distributed inference of deep neural networks for Edge AI (opens in a new tab)

  4. Digital phenotyping through multimodal, unobtrusive sensing

    … phenotyping data enables researchers to make inferences regarding users’ physical and mental health at scale, for the first time. However, translating this data into actionable insights requires computational approaches that turn unlabelled, multimodal time-series sensor data into validated …

    cambridge Repository record for Digital phenotyping through multimodal, unobtrusive sensing (opens in a new tab)

  5. Advances in Variational Bayes Theory: Adaptation, Uncertainty Quantification, and Amortization

    Variational methods and variational inference have been widely used in statistical physics, Bayesian posterior approximation, and modern generative modeling. At a high level, a variational method transforms an often difficult or intractable inference problem into an optimization problem by …

    maryland Repository record for Advances in Variational Bayes Theory: Adaptation, Uncertainty Quantification, and Amortization (opens in a new tab)

  6. Adaptive model inference under computational resource constraints

    Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-05-01

    uiuc Repository record for Adaptive model inference under computational resource constraints (opens in a new tab)