Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 6, Issue 6, 2022

A Survey on Bayesian Neural Networks

Download as PDF

DOI: 10.23977/acss.2022.060612 | Downloads: 25 | Views: 595

Author(s)

Hua Zhong 1, Lin Liu 1, Shicheng Liao 1

Affiliation(s)

1 Institute of Problem Solving, Yunnan Normal University, Kunming, China

Corresponding Author

Lin Liu

ABSTRACT

Bayesian Neural Network is the product of combining Bayesian and neural networks, which is one of the most popular neural network branches in deep learning and is widely used in model building in various fields. Bayesian inference is mainly divided into two types: variational inference and MCMC methods. Variational inference uses a pre-defined simple distribution to approximate the posterior distribution, which is faster and suitable for larger scale data. MCMC approach approaches the posterior distribution by sampling, which is more accurate, but relatively slower. This paper introduces three more representative Bayesian models and briefly introduces the main steps and formulas involved in the models. In addition, a variety of Bayesian neural network models are categorized and organized. Finally, the development of Bayesian is summarized and prospected.

KEYWORDS

bayesian, neural network, variational inference, MCMC

CITE THIS PAPER

Hua Zhong, Lin Liu, Shicheng Liao, A Survey on Bayesian Neural Networks. Advances in Computer, Signals and Systems (2022) Vol. 6: 81-87. DOI: http://dx.doi.org/10.23977/acss.2022.060612.

REFERENCES

[1] Baele G, Lemey P, Rambaut A, Suchard MA. Adaptive MCMC in Bayesian phylogenetics: an application to analyzing partitioned data in BEAST. Bioinformatics. 2017 Jun 15;33(12):1798-1805. doi: 10. 1093 /bioinformatics/ btx088.  PMID: 28200071; PMCID: PMC6044345.
[2] Saatci Y, Wilson A G. Bayesian gan[J]. Advances in neural information processing systems, 2017, 30.
[3] Wang, Jiaxing & Zhou, Zijun & Lin, Keli & Law, Chung & Yang, Bin. (2020). Facilitating Bayesian analysis of combustion kinetic models with artificial neural network. Combustion and Flame. 213. 87-97. 10. 1016/ j .combustflame.2019.11.035.
[4] Shridhar K, Laumann F, Liwicki M. A comprehensive guide to bayesian convolutional neural network with variational inference[J]. arXiv preprint arXiv:1901.02731, 2019.
[5] Chien J T, Kuo C L. Variational bayesian gan[C]//2019 27th European Signal Processing Conference (EUSIPCO). IEEE, 2019: 1-5.
[6] Chen T,  Fox E B,  Guestrin C. Stochastic Gradient Hamiltonian Monte Carlo[J]. Eprint Arxiv, 2014:1683-1691.
[7] Liu Ze-rui. Tea classification method based on Bayesian convolutional neural network [D]. Tianjin University of Commerce.
[8] Fortunato M,  Blundell C,  Vinyals O. Bayesian Recurrent Neural Networks[J].  2017.
[9] Pal S,  Valkanas A,  Regol F , et al. Bag Graph: Multiple Instance Learning using Bayesian Graph Neural Networks[J].  2022.
[10] Luo Y,  Huang Z,  Zhang Z, et al. Learning from the Past: Continual Meta-Learning with Bayesian Graph Neural Networks[C]// National Conference on Artificial Intelligence. Association for the Advancement of Artificial Intelligence (AAAI), 2020.
[11] Sun J,  Guo W,  Zhang D, et al. A Framework for Recommending Accurate and Diverse Items Using Bayesian Graph Convolutional Neural Networks[C]// KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ACM, 2020.
[12] Cong Y. Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC:, 10.48550/arXiv.1706.01724[P]. 2017.
[13] Fan X,  Li B ,  Li Y, et al. Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks[C]// International Conference on Machine Learning. PMLR, 2021.
[14] Zhou C,  Ban H,  Zhang J, et al. Gaussian Mixture Variational Autoencoder for Semi-Supervised Topic Modeling[J]. IEEE Access, 2020, PP(99):1-1.
[15] Eslami S,  Heess N,  Weber T, et al. Attend, Infer, Repeat: Fast Scene Understanding with Generative Models:, 10.48550/arXiv.1603.08575[P]. 2016.
[16] Karl M,  Soelch M,  Bayer J, et al. Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data[J].  2017.
[17] Flunkert V,  Salinas D,  Gasthaus J . DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks:, 10.1016/j.ijforecast.2019.07.001[P]. 2020.
[18] Watter M,  Springenberg J T,  Boedecker J , et al. Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images[J]. Advances in neural information processing systems, 2015.
[19] Bittig H C,  Steinhoff T,  Claustre H , et al. Bayesian Neural Networks[J]. Frontiers in Marine ence, 2018, 5.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 14646
Visits: 264671

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.