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 47 for “"discriminative models"”.

  1. Exploiting Domain Structure with Hybrid Generative-Discriminative Models

    … often face a tradeoff between the accuracy of discriminative models and the lower sample complexity of their generative counterparts. This inspires a need for hybrid methods. In this paper we present the graphical ensemble classifier (GEC), a novel combination of logistic regression and naive …

    oregon Repository record for Exploiting Domain Structure with Hybrid Generative-Discriminative Models (opens in a new tab)

  2. Generative and discriminative models for person verification and efficient search

    Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2013-04-10T20:41:56Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Li_Zhen.pdf: 10718613 bytes, checksum: 33d3a5f6a45d0870d945906fb9961656 (MD5)

    uiuc Repository record for Generative and discriminative models for person verification and efficient search (opens in a new tab)

  3. Contributions of Bayesian and Discriminative Models to Active Visual Perception across Saccades

    … is to investigate the relative contributions of Discriminative and Bayesian processes to active visual perception across saccades.</p><p>We performed a series of psychophysical, computational, and neural recording experiments grounded in variations of a task known as “saccadic suppression of …

    duke Repository record for Contributions of Bayesian and Discriminative Models to Active Visual Perception across Saccades (opens in a new tab)

  4. Advances in Generative and Discriminative Models for De Novo DNA Binder Design

    … powerful generative machine learning models for protein design, applied to DNA binders; 2. a computational pipeline for designing DNA binding proteins with the ability to discover sequence selective DNA binding proteins from as few as 96 designs tested in the wet lab, and 3. …

    washington Repository record for Advances in Generative and Discriminative Models for De Novo DNA Binder Design (opens in a new tab)

  5. Learning from text and images: generative and discriminative models for partially labeled data

    … learning problem and propose generative and discriminative models to tackle this learning problem. Multiple instance multiple label learning is a generalization of supervised learning in which the training examples are bags of instances and each bag is labeled with a set of labels. We explore …

    iastate Repository record for Learning from text and images: generative and discriminative models for partially labeled data (opens in a new tab)

  6. Hybrid Generative Models for 2D and 3D Computer Vision

    … in visual perception and imagination. Discriminative models have achieved human-level performance on several tasks. Generative models have also shown great promise for 2D and 3D synthesis; however, their performance still lags behind discriminative models. Several approaches have been …

    cornell Repository record for Hybrid Generative Models for 2D and 3D Computer Vision (opens in a new tab)

  7. A generative-discriminative framework for time-series data classification

    … two-stage framework that combines generative and discriminative models to reach a high performance in the classification of time-series data. In the first stage, HMMs are used to model the time-series data, then a fixed size score vector is extracted from this stage and used as the input to the …

    concordia Download PDF for A generative-discriminative framework for time-series data classification (opens in a new tab)

  8. Visual Object Recognition Using Generative Models of Images

    … the recognition problem has been to learn a discriminative model, i.e. a model of the conditional probability P(l|υ) over possible object labels l given an image υ. Here we consider an alternative class of models, broadly referred to as generative models, that learns the latent structure of …

    toronto-retro Repository record for Visual Object Recognition Using Generative Models of Images (opens in a new tab)

  9. TOWARDS ROBUST COMPUTER VISION USING SYNTHETIC DATA AND GENERATIVE MODELS

    … decade by deep neural networks, computer vision models are still not ready for many real-world applications due to insufficient robustness to out-of-distribution (OOD) scenarios. Their good performance on standard benchmarks does not seem to transfer well to deployment environments. The need for …

    jhu Repository record for TOWARDS ROBUST COMPUTER VISION USING SYNTHETIC DATA AND GENERATIVE MODELS (opens in a new tab)

  10. Healthcare innovations empowered by discriminative and generative artificial intelligence

    … (AI) is reshaping healthcare through discriminative and generative models, among other paradigms. Discriminative models classify data by learning boundaries, while generative models capture underlying distributions to produce new data. This dissertation advances both directions with …

    oklahoma-thes Repository record for Healthcare innovations empowered by discriminative and generative artificial intelligence (opens in a new tab)

  11. Modeling and Mapping Location-Dependent Human Appearance

    … and time. In our work, we build computational models to learn the relationship between human appearance, geographic location, and time. The primary contributions are a framework for collecting and processing geotagged imagery of people, a large dataset collected by our framework, and several …

    uky-thes Repository record for Modeling and Mapping Location-Dependent Human Appearance (opens in a new tab)

  12. THESIS TITLE: ADVANCES IN PUNCTUATION AND DISFLUENCY PREDICTION

    … approach. Our decoder can combine generative models like n-gram language models (LM) and discriminative models like Max-margin Markov Networks (M3N). Lastly, we have performed an empirical study on various state-of-the-art methods for combining the two tasks, and we have highlighted some …

    nus Repository record for THESIS TITLE: ADVANCES IN PUNCTUATION AND DISFLUENCY PREDICTION (opens in a new tab) Download file for THESIS TITLE: ADVANCES IN PUNCTUATION AND DISFLUENCY PREDICTION (opens in a new tab)

  13. Predictive Pattern Discovery in Dynamic Data Systems

    … was developed utilizing both generative and discriminative models to address the event prediction problem through optimization in multivariate systems. Secondly, in addition to modeling temporal dynamics, a Bayesian approach is employed to model the first-order Markov behavior in the …

    marquette Repository record for Predictive Pattern Discovery in Dynamic Data Systems (opens in a new tab)

  14. Towards Effective Yet Affordable Generative Models for Image Data

    The area of generative models, which encompasses a variety of approaches such as Generative Adversarial Networks, Variational Auto-encoders, Diffusion Models has become one of the most popular research topics in the field of machine learning recently. These models have exhibited an impressive …

    buffalo Repository record for Towards Effective Yet Affordable Generative Models for Image Data (opens in a new tab)

  15. Software bug management from bug reports to bug signatures

    … identification. In particular, we focus on how discriminative techniques can be applied to these two problems. For duplicate bug report retrieval, we propose two metrics to measure the similarity between bug reports, and optimize the metrics based on discriminative models. For bug signature …

    nus Repository record for Software bug management from bug reports to bug signatures (opens in a new tab) Download file for Software bug management from bug reports to bug signatures (opens in a new tab)

  16. A computational approach to gestural interactions of the upper limb on planar surfaces

    … new interactions remains, however, a challenge. Models have been used to foresee interaction properties: Fitts’ law, for example, accurately predicts movement time in pointing and steering tasks. But what happens when no existing models apply? The core assertion to this work is that a …

    glasgow Repository record for A computational approach to gestural interactions of the upper limb on planar surfaces (opens in a new tab) Download PDF for A computational approach to gestural interactions of the upper limb on planar surfaces (opens in a new tab)

  17. Methods For High Dimensional Matrix Computation And Diagnostics Of Distributed System

    … on system data early in the process. We study discriminative models in functional data analysis, and introduce generative models that capture server regime-change behaviors. We also design computational methods, including a blocked Gibbs sampler, to improve the accuracy and efficiency of model …

    cornell Repository record for Methods For High Dimensional Matrix Computation And Diagnostics Of Distributed System (opens in a new tab)

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

    … high-stakes domains. Despite strong performance, models remain prone to reliability issues such as overconfidence, hallucinations, and modality bias. This thesis addresses these challenges through post-hoc methods and targeted fine-tuning strategies. First, we mitigate overconfidence in …

    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)

  19. Combine and conquer: representation learning from multmodal data

    … accurately represented by a single label. When models are trained using this method, they often learn features that spuriously correlate with the label, resulting in poor performance when deployed in the real world.</p> <p>This thesis explores representation learning using multiple sources of …

    oxford Repository record for Combine and conquer: representation learning from multmodal data (opens in a new tab)

  20. Using Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks for Partially Occluded Object Recognition

    … We then test the hypothesis that generative models such as the Deep Belief Network should perform better on occluded object recognition tasks than purely discriminative models such as Convolutional Neural Networks. We find that the data does not support this hypothesis when the generative …

    concordia Download PDF for Using Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks for Partially Occluded Object Recognition (opens in a new tab)

Page 1 of 3