This repository provides an extensive, continuously updated survey of Bayesian Deep Learning (BDL), a framework for building robust models across diverse applications. It serves as a comprehensive resource for researchers and practitioners interested in probabilistic approaches to deep learning, offering categorized links to seminal papers, code, and datasets.

How It Works

The survey categorizes BDL research into application domains such as recommender systems, healthcare, NLP, computer vision, and time series forecasting, as well as foundational BDL concepts. It highlights key papers and their associated resources, providing a structured overview of the field's evolution and current state. The approach is to curate and organize existing literature, making it accessible and navigable for those exploring BDL.

Quick Start & Requirements

This repository is a curated list of academic papers and resources, not a software package. No installation or execution is required.

Highlighted Details

• Comprehensive coverage of BDL applications across 15+ domains.
• Links to over 200 research papers, many with associated code and datasets.
• Includes foundational work on Bayesian Neural Networks and probabilistic modeling.
• Features a 2020 ACM Computing Surveys publication as a core reference.

Maintenance & Community

The survey is actively updated by js05212, indicating ongoing maintenance. Specific community channels or contributor details are not provided in the README.

Licensing & Compatibility

The repository itself, as a collection of links and information, does not have a specific software license. The licenses of the linked papers and code repositories would vary.

Limitations & Caveats

This resource is a survey and does not provide executable code or a unified BDL framework. Users must individually access and evaluate the linked research papers and their respective implementations.