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 66 for “"Bayesian neural network"”.

  1. Modelling uncertainty in cloud workload forecasting: a Hybrid Bayesian Neural Network approach

    … This work introduces a novel Hybrid Bayesian Neural Network (HBNN) model designed to capture both types of uncertainty in workload forecasting by incorporating a Bayesian layer at the network's end. The HBNN surpasses conventional approaches by estimating the future probability …

    cork Repository record for Modelling uncertainty in cloud workload forecasting: a Hybrid Bayesian Neural Network approach (opens in a new tab)

  2. Unconventional reservoir parameter estimation by seismic inversion and machine learning of the Bakken Formation, North Dakota

    … seismic inversion followed by application of a Bayesian Neural Network to predict total porosity across the entire seismic volume given an estimated volume of P-impedance. The Bayesian Neural Network utilizes Markov Chain Monte Carlo via Langevin Dynamics in order to sample from the probability …

    texas Repository record for Unconventional reservoir parameter estimation by seismic inversion and machine learning of the Bakken Formation, North Dakota (opens in a new tab)

  3. Bayesian Neural Networks for SNP Identification: A Probabilistic Approach to Addressing GWAS Limitations

    … in plant genomes. The first study benchmarks a Bayesian neural network across multiple plant datasets and phenotype types, comparing it against established GWAS pipelines and a convolutional baseline, with biological validation through Gene Ontology analyses. The second develops an optimized …

    guelph Repository record for Bayesian Neural Networks for SNP Identification: A Probabilistic Approach to Addressing GWAS Limitations (opens in a new tab)

  4. Predictive flood mapping in cloud-obscured satellite imagery

    … image. Logistic regression, random forest, and neural networks were evaluated. To obtain prediction uncertainty estimates, a Bayesian neural network using Monte Carlo dropout was trained and compared to Logistic regression confidence intervals. Logistic regression and neural networks averaged …

    washington Repository record for Predictive flood mapping in cloud-obscured satellite imagery (opens in a new tab)

  5. Measuring Machine Learning Model Uncertainty with Applications to Aerial Segmentation

    … for measuring epistemic uncertainty and the Bayesian neural network. The latter replaces each trained weight with a random variable with which we approximate the true, unknown distribution of each weight with a two parameter (mean and variance) normal distribution. Bayes by Backprop trains …

    claremont Repository record for Measuring Machine Learning Model Uncertainty with Applications to Aerial Segmentation (opens in a new tab)

  6. Adversarial robustness of Bayesian neural networks

    … for computing local robustness of probabilistic neural networks, specifically those resulting from Bayesian inference. In theory, applying Bayesian inference to the learning of neural network parameters carries the promise of solving many practically vexing problems that arise under the …

    oxford Repository record for Adversarial robustness of Bayesian neural networks (opens in a new tab)

  7. Fetal gestational age estimation without clinical measurement using deep learning

    … This thesis therefore attempts to use deep neural network to directly regress gestational age from fetal standard planes without pixel size information, thus relying on anatomical appearance alone without fetal biometry.</p> <p>In this thesis, we first investigate the data augmentation …

    oxford Repository record for Fetal gestational age estimation without clinical measurement using deep learning (opens in a new tab)

  8. Visual bias mitigation driven by Bayesian uncertainties

    … of these intelligent models are variants of deep neural networks trained on large real-world datasets. These datasets reflect our historical and societal biases; in turn, AI learns these correlations during training resulting in predictors and decision-makers exhibiting racism, ableism, sexism and …

    whiterose Download PDF for Visual bias mitigation driven by Bayesian uncertainties (opens in a new tab)

  9. Injury prediction for Canadian mineral exploration using machine learning and time series

    … including Support Vector Machine, Convolutional Neural Network, Bayesian Neural Network, and more, along with four time series methods, were used. The findings offer critical insights into injury patterns, enabling the development of enhanced safety protocols. By providing quantitative …

    laurentian Repository record for Injury prediction for Canadian mineral exploration using machine learning and time series (opens in a new tab)

  10. Triatominae in North America : a comparison of statistical machine learning approaches for habitat suitability modelling

    … a single species model, a joint species Bayesian Linear Regression model [BLR], and a Bayesian Neural Network [BNN] adapted to model both joint, and single species distributions. It was found that the single species models perform well outside of the observed range of predictor variables, …

    texas Repository record for Triatominae in North America : a comparison of statistical machine learning approaches for habitat suitability modelling (opens in a new tab)

  11. Forecasting total factor productivity growth in the construction industry using neural network modelling

    … growth are complicatedly interacted, Artificial Neural networks (ANNs) are applied to solve such complex nonlinear mappings. To overcome overfitting caused by small dataset, Bayesian Neural Network (BNN) is adopted. The result shows that ANNs can model TFP growth more accurately than the …

    nus Repository record for Forecasting total factor productivity growth in the construction industry using neural network modelling (opens in a new tab) Download file for Forecasting total factor productivity growth in the construction industry using neural network modelling (opens in a new tab)

  12. Small-variance asymptotics for Bayesian neural networks

    Bayesian neural networks (BNNs) are a rich and flexible class of models that have several advantages over standard feedforward networks, but are typically expensive to train on large-scale data. In this thesis, we explore the use of small-variance asymptotics-an approach to yielding fast algorithms …

    bu Repository record for Small-variance asymptotics for Bayesian neural networks (opens in a new tab)

  13. NEURAL NETWORK MODEL INTERPRETABILITY FOR COMPUTER NETWORK OPERATIONS AND DEFENSE

    … cyberspace defense and incident response on Navy networks is predicated on the ability to quickly identify, characterize, classify, and respond to network events. A vast amount of network data is collected on shore and enterprise networks alike, but the quantity of data hinders rapid analysis and …

    nps Repository record for NEURAL NETWORK MODEL INTERPRETABILITY FOR COMPUTER NETWORK OPERATIONS AND DEFENSE (opens in a new tab)

  14. Survival Prediction of Pediatric Leukemia under Model Uncertainty

    … novel predictive models that incorporate Bayesian principles and advanced machine learning and deep learning techniques. Recognizing the complexity and heterogeneity of leukemia, our research emphasizes the need for precise and individualized predictions that factor in the recurrence and …

    oklahoma-thes Repository record for Survival Prediction of Pediatric Leukemia under Model Uncertainty (opens in a new tab)

  15. Algorithm-Hardware Co-design for Deep Learning and Probabilistic Computing with Compute-in-Memory Accelerators

    … on this simulator, the CIM systems for deep neural network (DNN) with limited on-chip resources are explored, addressing the challenge of accommodating large-scale models on area-constrained CIM chips, and the reconfiguration of deploying different models on prefabricated CIM chip with fixed …

    gatech Repository record for Algorithm-Hardware Co-design for Deep Learning and Probabilistic Computing with Compute-in-Memory Accelerators (opens in a new tab)

  16. Fatigue damage diagnostics and prognostics of composites using artificial intelligence methods for experimental data

    … based on machine learning (ML) and deep neural networks. The research question developed for this study was ‘Can fatigue damage classification and prognostics of composites be enhanced using artificial intelligence methods?’ The specific aims developed to answer the research question were …

    ttu Repository record for Fatigue damage diagnostics and prognostics of composites using artificial intelligence methods for experimental data (opens in a new tab)

  17. On the adversarial robustness of Bayesian machine learning models

    Bayesian machine learning (ML) models have long been advocated as an important tool for safe artificial intelligence. Yet, little is known about their vulnerability against adversarial attacks. Such attacks aim to cause undesired model behaviour (e.g. misclassification) by crafting small …

    oxford Repository record for On the adversarial robustness of Bayesian machine learning models (opens in a new tab)

  18. Robust localization with wearable sensors

    … robust long-term tracking systems with a Bayesian neural network and sequential Monte Carlo method, and (v) verifying that the system can be applied with changing modes of behaviour, defined as natural transitions from walking to running and vice versa. This research introduces a new …

    oxford Repository record for Robust localization with wearable sensors (opens in a new tab)

Page 1 of 4