A Systematic Comparison of Robustness in Bayesian Deep Learning on Diabetic Retinopathy Diagnosis Tasks
-
Updated
Nov 21, 2022 - Python
A Systematic Comparison of Robustness in Bayesian Deep Learning on Diabetic Retinopathy Diagnosis Tasks
My excursions in the world of Artificial Neural Networks
Implementing Bayes by Backprop with PyTorch. Applied on time-series prediction.
Benchmarking Bayesian Deep Learning for Out-of-Distribution Detection
Variational continual learning of a conditional diffusion model to generate MNIST. Based on 'Conditional Diffusion MNIST'.
Work as part of ANL summer 2020 research on uncertainity quanitification methods in graph neural networks
An implementation of natural parameter networks and its extension to GRUs in PyTorch
Active Learning with approximations of Bayesian Convolutional Neural Networks.
Inference Algorithms for Bayesian Deep Learning
Research-repository: Bayesian neural networks for predicting disruptions using EFIT and diagnostic data in KSTAR
Code accompanying ICLR 2024 paper "Function-space Parameterization of Neural Networks for Sequential Learning"
Empirical analysis of recent stochastic gradient methods for approximate inference in Bayesian deep learning, including SWA-Gaussian, MultiSWAG, and deep ensembles. See report_localglobal.pdf.
PyTorch implementation of the paper 'Weight Uncertainty in Neural Networks'
From Registration Uncertainty to Segmentation Uncertainty (ISBI 2024)
Codebase for BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts.
Awesome-spatial-temporal-scientific-machine-learning-data-mining-packages. Julia and Python resources on spatial and temporal data mining. Mathematical epidemiology as an application. Most about package information. Data Sources Links and Epidemic Repos are also included.
Langevin Gradient Parallel Tempering for Bayesian Neural Learning.
We provide two notebooks that enable users to explore and experiment with some BDL techniques as Ensembles, MC Dropout and Laplace Approximation. In this way, they allow you to intuitively visualize the main differences among them in a Simulated Dataset and Boston Dataset.
Add a description, image, and links to the bayesian-deep-learning topic page so that developers can more easily learn about it.
To associate your repository with the bayesian-deep-learning topic, visit your repo's landing page and select "manage topics."