no code implementations • 5 Jun 2020 • Sho Ichigozaki, Takahiro Kawashima, Hayaru Shouno
In this paper, we propose a Bayesian Graphical LASSO for correlated countable data and apply it to spatial crime data.
no code implementations • 2 Jun 2020 • Genta Kobayashi, Hayaru Shouno
In addition, we suggest that some inactive neurons in the first layer of ResNet affect the classification task.
no code implementations • 2 Apr 2019 • Takahiro Kawashima, Hayaru Shouno
Photon-limited images are often seen in fields such as medical imaging.
no code implementations • 16 Oct 2018 • Aiga Suzuki, Hayaru Shouno
Modeling of textures in natural images is an important task to make a microscopic model of natural images.
no code implementations • 15 Oct 2018 • Aiga Suzuki, Hidenori Sakanashi, Shoji Kido, Hayaru Shouno
Transfer learning is a machine learning technique designed to improve generalization performance by using pre-trained parameters obtained from other learning tasks.
1 code implementation • 29 Mar 2018 • Hideo Terada, Hayaru Shouno
We are trying to implement deep neural networks in the edge computing environment for real-world applications such as the IoT(Internet of Things), the FinTech etc., for the purpose of utilizing the significant achievement of Deep Learning in recent years.
no code implementations • 20 Jun 2017 • Kazuyuki Hara, Daisuke Saitoh, Hayaru Shouno
We find that the process of combining the neglected hidden units with the learned network can be regarded as ensemble learning, so we analyze dropout learning from this point of view.
no code implementations • 18 Jun 2015 • Hiroaki Sasaki, Michael U. Gutmann, Hayaru Shouno, Aapo Hyvärinen
The precision matrix of the linear components is assumed to be randomly generated by a higher-order process and explicitly parametrized by a parameter matrix.
1 code implementation • 7 Dec 2014 • Hayaru Shouno
In our formulation, we interpret the observation through the Poisson noise channel as a likelihood, and evaluate the bound of it with a Gaussian function using a latent variable method.