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 8 of 8 for “"Learning to search"”.

  1. LEARNING-TO-SEARCH APPROACHES FOR VEHICLE ROUTING PROBLEMS USING DEEP REINFORCEMENT LEARNING

    Recently, Deep Reinforcement Learning (DRL) has been harnessed to develop generic, adaptable, and data-driven solvers for Vehicle Routing Problems (VRPs). Among them, Learning-to-Search (L2S) solvers are promising yet largely constrained by existing design limitations. This thesis aims to …

    nus Repository record for LEARNING-TO-SEARCH APPROACHES FOR VEHICLE ROUTING PROBLEMS USING DEEP REINFORCEMENT LEARNING (opens in a new tab) Download file for LEARNING-TO-SEARCH APPROACHES FOR VEHICLE ROUTING PROBLEMS USING DEEP REINFORCEMENT LEARNING (opens in a new tab)

  2. Using iterated learning to search for the linear-additive bias in multiple-cue judgment

    … number of ways that the cues could relate to the outcome. So, how do people efficiently learn in a multiple-cue judgment task? Based on the findings of decades of experimental and naturalistic measurements, researchers have proposed that human judges have innate biases to expect that the …

    unsw Repository record for Using iterated learning to search for the linear-additive bias in multiple-cue judgment (opens in a new tab)

  3. Learning-based search algorithm design

    Classical search algorithms, such as A* search, evolutionary search, and Monte Carlo tree search, play a central role in solving many combinatorial optimization problems, including robotic path planning, molecule optimization, and playing Go. Conventionally, domain experts design these algorithms …

    gatech Repository record for Learning-based search algorithm design (opens in a new tab)

  4. Towards Robust and Generalizable Intelligence through Adversarial Examination and Generative Models

    Deep learning systems achieve strong performance on tasks ranging from image recognition and 3D pose estimation to visual content generation and large-scale language modeling. Yet these models remain brittle: they can fail under distribution shifts, exhibit systematic vulnerabilities to small but …

    jhu Repository record for Towards Robust and Generalizable Intelligence through Adversarial Examination and Generative Models (opens in a new tab)

  5. Advancing vision-language understanding through fine-grained perception and long-range modeling

    … but insufficient selectivity: the inability to maintain stable, semantically persistent representations—perceptual anchors—across the noise of dynamic scenes and the vastness of long-range multimodal contexts. A model that cannot preserve what it has seen will hallucinate; a model that cannot …

    lmu-germany Repository record for Advancing vision-language understanding through fine-grained perception and long-range modeling (opens in a new tab)

  6. Towards Practical Machine Learning for Program Analysis and Optimisation

    Machine learning (ML), such as supervised learning and deep reinforcement learning (DRL) techniques, has shown great potential in code-related tasks such as predicting code optimisation options and detecting software bugs. However, its practical use still faces multiple hurdles during the model …

    whiterose Download PDF for Towards Practical Machine Learning for Program Analysis and Optimisation (opens in a new tab)

  7. Extending peptide search space and self-assembly methods

    … has been a general shift from reducing proteins to shorter functional sequences to design peptide nanomaterials from the bottom up. Shorter peptides are often cheaper and easier to produce while still possessing a large combinatorial chemical space that can be exploited for drug delivery systems, …

    strathclyde Repository record for Extending peptide search space and self-assembly methods (opens in a new tab)

  8. A machine learning investigation of asteroid classification in the optical regime

    Historically, asteroids have been characterised by features of their reflectance spectra in the optical and near-infrared (NIR) as well as their albedos. The Bus-DeMeo asteroid taxonomy and its closely-related predecessor (Bus-Binzel) both have their roots in spectrophotometric work from the 1970s …

    liverpool-jm Repository record for A machine learning investigation of asteroid classification in the optical regime (opens in a new tab) Download PDF for A machine learning investigation of asteroid classification in the optical regime (opens in a new tab)