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 40 for “"Sparse datasets"”.

  1. Scaling Machine Learning Data Repair Systems for Sparse Datasets

    … performance for the data repair problem on many datasets. However, these systems face significant challenges with sparse datasets. In this work, the challenges presented by such datasets to machine learning data repair systems are investigated. Dataset-independent methods are presented to …

    waterloo Repository record for Scaling Machine Learning Data Repair Systems for Sparse Datasets (opens in a new tab)

  2. A Distributed, Architecture-Centric Approach to Computing Accurate Recommendations from Very Large and Sparse Datasets

    … information is abundant. There are many large datasets available for analysis because many businesses are interested in future user opinions. Sophisticated algorithms that predict such opinions can simplify decision-making, improve customer satisfaction, and increase sales. However, modern …

    ku Repository record for A Distributed, Architecture-Centric Approach to Computing Accurate Recommendations from Very Large and Sparse Datasets (opens in a new tab)

  3. Studies on applications of neural networks in modeling sparse datasets and in the analysis of dynamics of CA3 in hippocampus

    … the resulting classification models over several datasets and demonstrated that the \gls{regularization}s we employed in our heuristics, had a positive effect on the performance of the data model across various classification problems as well. In the second part of this dissertation, we focused on …

    uvic Repository record for Studies on applications of neural networks in modeling sparse datasets and in the analysis of dynamics of CA3 in hippocampus (opens in a new tab)

  4. Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska

    Neural networks (NNs) are widely used to investigate the relationship among variables in complex multivariate problems. In cases of limited data, the network behavior strongly depends on factors such as the choice of network activation function and network initial weights. In this study, I …

    tamu Repository record for Neural network analysis of sparse datasets ?? an application to the fracture system in folds of the Lisburne Formation, northeastern Alaska (opens in a new tab)

  5. Frequency-domain Data Assimilation of Periodic Flow using Physics-informed Neural Networks

    … measurements of fluid flows are often sparse, made up of velocity or pressure measurements taken at discrete spatial locations with gaps between them. This spatial sparsity limits the accuracy of techniques that seek to infer unsteady forces, energy transfer, or distill dynamical models …

    calgary Repository record for Frequency-domain Data Assimilation of Periodic Flow using Physics-informed Neural Networks (opens in a new tab)

  6. Restricted Isometric Projections for Differentiable Manifolds and Applications

    … sensing. In RN, RIP establishes the success of sparse recovery via basis pursuit for measurement matrices with small restricted isometry constants δ2s < 1=3. A weaker condition, δ2s < 0:6246, is actually sufficient to guarantee stable and robust recovery of all s-sparse vectors via …

    usf Repository record for Restricted Isometric Projections for Differentiable Manifolds and Applications (opens in a new tab)

  7. Uncertainty-Aware Data-Driven Approaches for Modelling Sparse Agricultural Datasets to Sustain a Society

    … of my dissertation is to tackle the issue of sparse datasets in case of agricultural domain to design data-driven approaches that can be used to make Decision Support Systems (DSS) for optimal growth of plants, thereby reducing the cost of labor as well as improving the overall food security …

    tamu Repository record for Uncertainty-Aware Data-Driven Approaches for Modelling Sparse Agricultural Datasets to Sustain a Society (opens in a new tab)

  8. HYBRID SIS AND MARKOV CHAIN MONTE CARLO SAMPLING METHODOLOGY FOR GOODNESS-OF-FIT TESTS ON CONTINGENCY TABLES

    … tests, however, may not be valid for sparse datasets having cell counts less than 5. In these cases, we often attempt exact conditional inference via a sampler, such as Markov Chain Monte Carlo (MCMC) or Sequential Importance Sampling (SIS). This paper proposes a hybrid sampling scheme …

    nps Repository record for HYBRID SIS AND MARKOV CHAIN MONTE CARLO SAMPLING METHODOLOGY FOR GOODNESS-OF-FIT TESTS ON CONTINGENCY TABLES (opens in a new tab)

  9. How to manage an uncommon alien rodent on a protected island?

    … such as capture-recapture to the collected datasets. Nonetheless, alien species that have low capture rates, such as small mammals, might present a considerable obstacle for conservation, as available capturerecapture models need a relatively large dataset to precisely and accurately …

    qucosa-diss

  10. Intelligent Inside Threat Detection Framework Based on Digital Twin, Transformer Variant Models, and Transfer Learning

    … experiments on CERT r4.2 (dense) and CERT r6.2 (sparse) datasets show that DistilledTrans, a customized transformer model, outperforms baseline models in accuracy, precision, recall, F1-score, and AUC, while being computationally efficient. To overcome challenges like data privacy and resource …

    ottawa-retro Repository record for Intelligent Inside Threat Detection Framework Based on Digital Twin, Transformer Variant Models, and Transfer Learning (opens in a new tab)

  11. On the Suitability of Machine Learning Approaches for Long-horizon Power Demand Forecasting in Gothenburg

    … time series models were fitted to two datasets of differing temporal coverage and sampling frequency, incorporating target variable data provided by Göteborg Energi alongside publicly available exogenous features. Under the available data, all models projected a continually constant …

    chalmers Repository record for On the Suitability of Machine Learning Approaches for Long-horizon Power Demand Forecasting in Gothenburg (opens in a new tab)

  12. Automatic Learning of Augmentation Strategies Based on Deep Learning Generative Models

    … learns an augmentation strategy appropriate for sparse datasets and can be used to improve pixel-level semantic segmentation accuracy by filling the gaps in the training set. The contributions of this thesis are summarised as follows. (1) Initially, in the image synthesis domain, we propose two …

    aston Download PDF for Automatic Learning of Augmentation Strategies Based on Deep Learning Generative Models (opens in a new tab)

  13. Applied Bayesian inference for diachronic meaning change

    … aspect is important for modelling the small and sparse datasets used in our main application. Significant gains are achieved in terms of predictive accuracy, ground-truth recovery, sampling efficiency and scalability. An intuitive method for selecting the learning rate in a generalised Bayes' …

    oxford Repository record for Applied Bayesian inference for diachronic meaning change (opens in a new tab)

  14. ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning

    … interaction sequences and item descriptions in sparse datasets. This work represents the first comprehensive study of LLM-generated reasoning in personalized recommendations, opening a new avenue for integrating human-like reasoning into recommender systems.

    tamu Repository record for ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning (opens in a new tab) Embargoed until 2026-12-01

  15. Evolutionary & Physics Infused Learning for Intelligent Systems

    … especially when trained with small or sparse datasets. Artificial Neural networks or ANNs are playing an emerging role as decision support models in various intelligent autonomous systems. This emergence is partly attributed to the capability of ANNs to serve as universal function …

    buffalo Repository record for Evolutionary & Physics Infused Learning for Intelligent Systems (opens in a new tab)

  16. Wound healing, a multidisciplinary approach: combining mathematical models and biological experiments

    … frequently generate spatially and temporally sparse datasets. We propose a range of techniques that allow the size, cellular processes and scar tissue properties of wounds to be measured and predicted at high spatial and temporal resolution. A non-invasive wound imaging system is shown to …

    whiterose Download PDF for Wound healing, a multidisciplinary approach: combining mathematical models and biological experiments (opens in a new tab)

  17. Interpolation of sparse data in hadron physics with Gaussian processes

    … of experimental data is complicated by their sparse, heterogeneous and multidimensional nature. This thesis develops a Gaussian Process (GP) framework for constructing continuous, uncertainty-aware representations of hadron physics observables across kinematic phase space. A central …

    glasgow Repository record for Interpolation of sparse data in hadron physics with Gaussian processes (opens in a new tab) Download PDF for Interpolation of sparse data in hadron physics with Gaussian processes (opens in a new tab)

  18. Towards efficacy and efficiency in sparse delay tolerant networks

    … approaches to handle message delivery in notably sparse DTNs. First, the ChitChat system [69] employs the social interests of individuals participating in a DTN to accurately model multi-hop relationships and to make opportunistic routing decisions for interest-annotated messages. Second, the …

    must-thes Repository record for Towards efficacy and efficiency in sparse delay tolerant networks (opens in a new tab)

  19. Advancing Quantitative Abdominal MRI: Methods for Highly Accelerated T2 Mapping with Radial Turbo Spin-Echo Sequences

    … to create high-quality images from incomplete datasets. We aim to improve highly accelerated abdominal T2 mapping using RADTSE via three main avenues. First, we develop pulse sequences that sample data more efficiently and strategically. Second, we improve the image reconstruction process using …

    arizona-thes Repository record for Advancing Quantitative Abdominal MRI: Methods for Highly Accelerated T2 Mapping with Radial Turbo Spin-Echo Sequences (opens in a new tab)

Page 1 of 2