no code implementations • 4 Jul 2023 • Shuya Nagayasu, Sumio Watanabe
The upper bound of free energy of Bayesian CNN with skip connection does not depend on the oveparametrization and, the generalization error of Bayesian CNN has similar property.
no code implementations • 28 Mar 2023 • Shuya Nagayasu, Sumio Watanabe
In many research fields in artificial intelligence, it has been shown that deep neural networks are useful to estimate unknown functions on high dimensional input spaces.
no code implementations • 10 Mar 2023 • Naoki Yoshida, Sumio Watanabe
Tensor decomposition is now being used for data analysis, information compression, and knowledge recovery.
no code implementations • 18 Nov 2022 • Sumio Watanabe
Two mathematical solutions and three applications to statistics based on algebraic geometry reported in this article are now being used in many practical fields in data science and artificial intelligence.
no code implementations • 11 Jun 2022 • Sumio Watanabe
We introduce a place of mathematical theory of Bayesian statistics for unknown uncertainty, which clarifies general properties of cross validation, information criteria, and marginal likelihood, even if an unknown data-generating process is unrealizable by a model or even if the posterior distribution cannot be approximated by any normal distribution.
no code implementations • 14 Mar 2022 • Takumi Watanabe, Sumio Watanabe
Multinomial mixtures are widely used in the information engineering field, however, their mathematical properties are not yet clarified because they are singular learning models.
no code implementations • 15 Dec 2020 • Shuya Nagayasu, Sumio Watanabe
Bayesian inference is a widely used statistical method.
Bayesian Inference Statistics Theory Statistics Theory 62F15
no code implementations • 13 Sep 2017 • Naoki Hayashi, Sumio Watanabe
Latent Dirichlet allocation (LDA) is useful in document analysis, image processing, and many information systems; however, its generalization performance has been left unknown because it is a singular learning machine to which regular statistical theory can not be applied.
no code implementations • 13 Dec 2016 • Naoki Hayashi, Sumio Watanabe
Non-negative matrix factorization (NMF) is a new knowledge discovery method that is used for text mining, signal processing, bioinformatics, and consumer analysis.
no code implementations • 27 Mar 2015 • Sumio Watanabe
By the formula, three facts are clarified about predictive prior design.