principledpruningbnn
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.9%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: biaslab
- Language: Jupyter Notebook
- Default Branch: main
- Size: 2.53 MB
Statistics
- Stars: 5
- Watchers: 4
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization
By Jim Beckers, Bart van Erp, Ziyue Zhao, Kirill Kondrashov and Bert de Vries
Published in the IEEE Open Journal of Signal Processing
Abstract
Bayesian model reduction provides an efficient approach for comparing the performance of all nested sub-models of a model, without re-evaluating any of these sub-models. Until now, Bayesian model reduction has been applied mainly in the computational neuroscience community on simple models. In this paper, we formulate and apply Bayesian model reduction to perform principled pruning of Bayesian neural networks, based on variational free energy minimization. Direct application of Bayesian model reduction, however, gives rise to approximation errors. Therefore, a novel iterative pruning algorithm is presented to alleviate the problems arising with naive Bayesian model reduction, as supported experimentally on the publicly available UCI datasets for different inference algorithms. This novel parameter pruning scheme solves the shortcomings of current state-of-the-art pruning methods that are used by the signal processing community. The proposed approach has a clear stopping criterion and minimizes the same objective that is used during training. Next to these benefits, our experiments indicate better model performance in comparison to state-of-the-art pruning schemes.
This repository contains all experiments of the paper.
Owner
- Name: BIASlab
- Login: biaslab
- Kind: organization
- Email: info@biaslab.org
- Location: Eindhoven, the Netherlands
- Website: http://biaslab.org
- Repositories: 47
- Profile: https://github.com/biaslab
Bayesian Intelligent Autonomous Systems lab
Citation (Citation.cff)
cff-version: 1.2.0
message: "Please cite this research as below."
authors:
- family-names: "Beckers"
given-names: "Jim"
- family-names: "van Erp"
given-names: "Bart"
orcid: "https://orcid.org/0000-0002-5619-7071"
- family-names: "Zhao"
given-names: "Ziyue"
- family-names: "Kondrashov"
given-names: "Kirill"
- family-names: "de Vries"
given-names: "Bert"
title: "Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization"
url: "https://github.com/biaslab/PrincipledPruningBNN"
preferred-citation:
type: article
authors:
- family-names: "Beckers"
given-names: "Jim"
- family-names: "van Erp"
given-names: "Bart"
orcid: "https://orcid.org/0000-0002-5619-7071"
- family-names: "Zhao"
given-names: "Ziyue"
- family-names: "Kondrashov"
given-names: "Kirill"
- family-names: "de Vries"
given-names: "Bert"
doi: "10.1109/OJSP.2023.3337718"
journal: "IEEE Open Journal of Signal Processing"
title: "Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization"
year: 2024
volume: 5
GitHub Events
Total
Last Year
Issues and Pull Requests
Last synced: about 1 year ago
All Time
- Total issues: 1
- Total pull requests: 3
- Average time to close issues: less than a minute
- Average time to close pull requests: 3 days
- Total issue authors: 1
- Total pull request authors: 2
- Average comments per issue: 0.0
- Average comments per pull request: 0.67
- Merged pull requests: 3
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- bartvanerp (1)
Pull Request Authors
- bartvanerp (2)
- JimBeckers (1)