Zobrazeno 1 - 10
of 1 820
pro vyhledávání: '"Watanabe Sumio"'
Autor:
Watanabe, Sumio
Mathematical equivalence between statistical mechanics and machine learning theory has been known since the 20th century, and researches based on such equivalence have provided novel methodology in both theoretical physics and statistical learning th
Externí odkaz:
http://arxiv.org/abs/2406.10234
Autor:
Nagayasu, Shuya, Watanabe, Sumio
Since the success of Residual Network(ResNet), many of architectures of Convolutional Neural Networks(CNNs) have adopted skip connection. While the generalization performance of CNN with skip connection has been explained within the framework of Ense
Externí odkaz:
http://arxiv.org/abs/2307.01417
Autor:
Nagayasu, Shuya, Watanabe, Sumio
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. However, their generalization performance is not yet completely clarified from
Externí odkaz:
http://arxiv.org/abs/2303.15739
Autor:
Yoshida, Naoki, Watanabe, Sumio
Tensor decomposition is now being used for data analysis, information compression, and knowledge recovery. However, the mathematical property of tensor decomposition is not yet fully clarified because it is one of singular learning machines. In this
Externí odkaz:
http://arxiv.org/abs/2303.05731
Autor:
Watanabe, Sumio
This article is a review of theoretical advances in the research field of algebraic geometry and Bayesian statistics in the last two decades. Many statistical models and learning machines which contain hierarchical structures or latent variables are
Externí odkaz:
http://arxiv.org/abs/2211.10049
Autor:
Watanabe, Sumio
In statistical inference, uncertainty is unknown and all models are wrong. That is to say, a person who makes a statistical model and a prior distribution is simultaneously aware that both are fictional candidates. To study such cases, statistical me
Externí odkaz:
http://arxiv.org/abs/2206.05630
Autor:
Watanabe, Takumi, Watanabe, Sumio
Multinomial mixtures are widely used in the information engineering field, however, their mathematical properties are not yet clarified because they are singular learning models. In fact, the models are non-identifiable and their Fisher information m
Externí odkaz:
http://arxiv.org/abs/2203.06884