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 10178 for “"deep"”.

  1. Deep-Sea Environment

    <p>The deep-sea environment is divided into three zones: the abyssopelagic, the abyssobenthic, and the hadal zones. The ocean floor is not a smooth featureless sedimentary plain as has been believed earlier, but instead it is of rough topography with numerous irregularities, deep depressions, many …

    nodak Repository record for Deep-Sea Environment (opens in a new tab)

  2. Deep Embedding Kernel

    Kernel methods and deep learning are two major branches of machine learning that have achieved numerous successes in both analytics and artificial intelligence. While having their own unique characteristics, both branches work through mapping data to a feature space that is supposedly more …

    kennesaw Repository record for Deep Embedding Kernel (opens in a new tab)

  3. Evolutionary deep learning

    … active areas of machine learning research. Deep neural networks are exhibiting an explosion in the number of parameters that need to be trained, as well as the number of permutations of possible network architectures and hyper-parameters. There is little guidance on how to choose these and …

    cape-town Repository record for Evolutionary deep learning (opens in a new tab)

  4. Deep linguistic lensing

    Language models and semantic word embeddings have become ubiquitous as sources for machine learning features in a wide range of predictive tasks and real-world applications. We argue that language models trained on a corpus of text can learn the linguistic biases implicit in that corpus. We discuss …

    mit Repository record for Deep linguistic lensing (opens in a new tab)

  5. The Deep Rendering Model: Bridging Theory and Practice in Deep Learning

    … in speech recognition. Recently, a new breed of deep learning algorithms has emerged for high-nuisance inference tasks; they are constructed from many layers of alternating linear and nonlinear processing units and are trained using large-scale algorithms and massive amounts of training data. The …

    rice Repository record for The Deep Rendering Model: Bridging Theory and Practice in Deep Learning (opens in a new tab)

  6. Deep neural networks are lazy : on the inductive bias of deep learning

    Deep learning models exhibit superior generalization performance despite being heavily overparametrized. Although widely observed in practice, there is currently very little theoretical backing for such a phenomena. In this thesis, we propose a step forward towards understanding generalization in …

    mit Repository record for Deep neural networks are lazy : on the inductive bias of deep learning (opens in a new tab)

  7. On Deep Network Optimization

    … learning, critical for training large and deep networks that have become prevalent in recent years. These networks demand significant computational resources, motivating research into improving the efficiency and effectiveness of the optimization process. We focus on two optimization …

    bielefeld Repository record for On Deep Network Optimization (opens in a new tab)

  8. Deep sea seismic stratigraphy

    … for the reflection of seismic waves within deep-sea sediments are shown to be less reliable for the purposes of correlation than their counter-parts in shallow margin sequences. Similar surfaces, such as abrupt lithological changes and unconformities, in the two different realms are not …

    the-open-u Repository record for Deep sea seismic stratigraphy (opens in a new tab)

  9. Structure-aware Deep Learning

    … methods that extend the scope of structure-aware deep learning through structural knowledge integration and enrichment, structural performance prediction, and synergistic transfer learning. Knowledge graphs organize information and make it directly available for querying. They provide a structured …

    passau-thes Repository record for Structure-aware Deep Learning (opens in a new tab)

  10. Deep in-memory computing

    … applications, this dissertation proposes deep in-memory accelerator (DIMA), which deeply embeds computation into the memory array, employing two key principles: (1) accessing and processing multiple rows of memory array at a time, and (2) embedding pitch-matched low-swing analog processing …

    uiuc Repository record for Deep in-memory computing (opens in a new tab)

  11. Designing for Deep Engagement

    … four novel interventions to promote states of deep engagement. Evaluating whether one of these interventions has a meaningful impact on flow state is difficult to do. The bulk of my work, then, focuses on the methodological challenges of flow state research. Herein I tackle three weaknesses in …

    mit Repository record for Designing for Deep Engagement (opens in a new tab)

  12. Guiding Deep Probabilistic Models

    Deep probabilistic models utilize deep neural networks to learn probability distributions in high-dimensional data spaces. Learning and inference in these models are complicated due to the difficulty of direct evaluation of the differences between the model distribution and the target. This thesis …

    mit Repository record for Guiding Deep Probabilistic Models (opens in a new tab)

  13. Deep penetration magnetoquasistatic sensors

    … including static (DC) operation, which enables deep penetration defect imaging. Low frequencies are needed for deep probing of metals, where the depth of penetration is otherwise limited by the skin depth due to the shielding effect of induced eddy currents. The capability to perform such …

    mit Repository record for Deep penetration magnetoquasistatic sensors (opens in a new tab)

  14. Evidential Deep Learning for uncertainty quantification in jet tagging deep neural network model

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01

    uiuc Repository record for Evidential Deep Learning for uncertainty quantification in jet tagging deep neural network model (opens in a new tab)

  15. Deep pockets: The economics of deep learning and the emergence of new AI platforms

    … time consuming. This is particularly true for deep learning, which is the most important machine learning technique of the past decade. Also, the benefits and costs of deep learning systems scale differently with performance and deployment size, which leads to different organizations …

    mit Repository record for Deep pockets: The economics of deep learning and the emergence of new AI platforms (opens in a new tab)

  16. PATIENT CLASSIFICATION USING DEEP LEARNING

    … deemed not possible a few years ago. Moreover, deep learning, one specific branch of artificial intelligence, has been used to produce useful results. It has been used in many new technologies such as self-driving cars, natural language processing, and many other automated systems. This research …

    unr Repository record for PATIENT CLASSIFICATION USING DEEP LEARNING (opens in a new tab)

  17. Deep Abyss: Repository of Echoes

    <p><em>Deep Abyss: Repository of Echoes</em> explores memory, trauma, and healing through an immersive, multi-sensory installation combining sound, video, and tactile elements. Focusing on sensory experience and embodied resonance, the work invites viewers to deeply engage with fragmented memories …

    wustl Repository record for Deep Abyss: Repository of Echoes (opens in a new tab)

  18. On deep learning in physics

    Machine learning, and most notably deep neural networks, have seen unprecedented success in recent years due to their ability to learn complex nonlinear mappings by ingesting large amounts of data through the process of training. This learning-by-example approach has slowly made its way into the …

    uoit Repository record for On deep learning in physics (opens in a new tab)

Page 1 of 509