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 16 of 16 for “"Bayesian Neural Networks (BNNs)"”.
-
Application of hierarchical bayes models to modelling of distribution of firm size by employees /
This thesis investigates the application of Bayesian hierarchical models and machine learning methods, such as Bayesian Additive Regression Trees (BART) and Bayesian Neural Networks (BNNs), to the modeling of distribution of firm size by employees, size classes, industries and countries. By …
-
Inference of Extreme Value Distributions using Bayesian Neural Networks
… of such extreme events. On the other hand, Bayesian Neural Networks (BNNs) extend traditional neural networks by incorporating Bayesian inference, which provides a probabilistic approach to learning and prediction in any given regression task. In this thesis, we extend the methodology of a …
-
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 …
-
CONFIDENTLY DETECTING OUT-OF-DISTRIBUTION SIGNALS WITH UNCERTAINTY
… methods use the standard probability output of neural networks to assess the model's confidence in its classification. The uncertainty-based methods use Bayesian neural networks (BNNs) to extract the model uncertainty to identify OOD observations. The Gradient-based methods probe the internal …
-
Propagating Uncertainty with Physics-Infused Machine Learning Models
… including Multi-Output Gaussian Processes (GPs), Bayesian Neural Networks (BNNs), and Spectral Normalized Gaussian Processes (SNGPs), are incorporated into the PIML framework to enhance uncertainty estimation. These hybrid models are evaluated on a synthetic benchmark problem and a real-world …
-
GAUSSIAN PROCESSES FOR SATELLITE DATA
Using convolutional neural networks (CNNs) on satellite data sets outperforms previous meteorological methods for classifying weather events from space-based sensor data. However, CNNs alone lack the ability to quantify the uncertainty about their prediction given the input to the model. Gaussian …
-
Robust Data-driven Predictive Control of Nonlinear Systems Under Modeling Uncertainty
… by limited data and numerical calculations, Bayesian Neural Networks (BNNs) are used, and their uncertainty estimates are integrated into two robust control approaches. The first is a scenario-based MPC (ScMPC) scheme that performs multi-stage optimization to account for uncertainty. The …
-
Nonparametric Bayesian Deep Learning for Scientific Data Analysis
… Gaussian processes (GPs) are nonparametric Bayesian models that are naturally robust to overfitting and offer UQ out-of-the-box. Unfortunately, traditional GP methods lack the balance of expressivity and domain-specific inductive bias that is key to the success of DL. Recently, however, a …
-
Exploring planetary surfaces: Active learning for resource mapping with autonomous rovers
… evaluates the performance differences of GPs and Bayesian Neural Networks (BNNs) in constrained trajectory exploration. The findings indicate that GPs consistently achieve faster convergence, require fewer samples, and result in shorter travel distances compared to BNNs. Despite the flexibility of …
-
Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies
… AI technologies, such as deep convolutional neural networks (DNNs), have recently achieved amazing success in numerous applications, such as image recognition, autonomous driving, and so on. However, there are two critical issues in the conventional DNN applications. The first problem is …
-
Quantitative histology for assessing organ health
… extraction workflow based on convolutional neural networks (CNN) to automatically segment different tissue compartments in renal biopsies. We design handcrafted features and qualitatively show that some of these features can capture visual changes related to chronic and acute injuries.</p> …
-
Learning under Data Irregularity and Uncertainty
… arise in widely used ML models, such as Deep Neural Networks (DNNs). This is exacerbated when considering their robustness and generalizability in real-world safety-critical applications such as autonomous driving and healthcare. It is therefore important to have accurate predictions as well …
-
NOVEL BAYESIAN NEURAL NETWORKS AND UNCERTAINTY QUANTIFICATION OF COMPUTATIONAL MECHANICS MODELS
… learning models. Amongst these methods, the Bayesian Neural Networks (BNNs) are widely used due to their strong mathematical foundation to quantify uncertainties through their stochastic parameters. Despite their wide application, they suffer from limitations such as instability in …
-
Reliable and Interpretable Machine Learning for Modeling Physical and Cyber Systems
… of several deterministic and stochastic Neural-Network models on modeling the dynamics of physical systems. We present an approach that uses Bayesian Neural Networks (BNNs) to model system dynamics under uncertainty. The BNN model is used to find optimal plan trajectories that take the …
-
Advances in Markov chain Monte Carlo for Bayesian deep learning for uncertainty quantification at scale
Bayesian neural networks (BNNs) provide a principled framework for epistemic uncertainty quantification in deep learning. Therein posterior inference is commonly approached through optimization-based approximations such as variational inference and the Laplace approximation, which scale well but …
-
Variational bayes deep neural network : theory, methods and applications
Bayesian neural networks (BNNs) have achieved state-of-the-art results in a wide range of tasks, especially in high dimensional data analysis, including image recognition, biomedical diagnosis and others. My thesis mainly focuses on high-dimensional data, including simulated data and brain images …