no code implementations • 3 Sep 2022 • Hideitsu Hino, Shotaro Akaho, Noboru Murata
The Expectation--Maximization (EM) algorithm is a simple meta-algorithm that has been used for many years as a methodology for statistical inference when there are missing measurements in the observed data or when the data is composed of observables and unobservables.
no code implementations • 7 Jan 2020 • Toshimitsu Aritake, Hideitsu Hino, Shigeyuki Namiki, Daisuke Asanuma, Kenzo Hirose, Noboru Murata
Single molecule localization microscopy is widely used in biological research for measuring the nanostructures of samples smaller than the diffraction limit.
no code implementations • 27 Sep 2019 • Shotaro Akaho, Hideitsu Hino, Noboru Murata
In this paper, we examine a geometrical projection algorithm for statistical inference.
no code implementations • 19 May 2018 • Sho Sonoda, Isao Ishikawa, Masahiro Ikeda, Kei Hagihara, Yoshihiro Sawano, Takuo Matsubara, Noboru Murata
We prove that the global minimum of the backpropagation (BP) training problem of neural networks with an arbitrary nonlinear activation is given by the ridgelet transform.
no code implementations • 12 Dec 2017 • Sho Sonoda, Noboru Murata
The feature map obtained from the denoising autoencoder (DAE) is investigated by determining transportation dynamics of the DAE, which is a cornerstone for deep learning.
no code implementations • 10 May 2016 • Sho Sonoda, Noboru Murata
Starting from the shallow DAE, this paper develops three topics: the transport map of the deep DAE, the equivalence between the stacked DAE and the composition of DAEs, and the development of the double continuum limit or the integral representation of the flow representation.
no code implementations • 2 Dec 2015 • Toshiyuki Kato, Hideitsu Hino, Noboru Murata
A large number of image super resolution algorithms based on the sparse coding are proposed, and some algorithms realize the multi-frame super resolution.
no code implementations • 14 May 2015 • Sho Sonoda, Noboru Murata
This paper presents an investigation of the approximation property of neural networks with unbounded activation functions, such as the rectified linear unit (ReLU), which is the new de-facto standard of deep learning.
no code implementations • 17 Feb 2014 • Toshiyuki Kato, Hideitsu Hino, Noboru Murata
Relative displacements of small patches of observed low-resolution images are accurately estimated by a computationally efficient block matching method.
no code implementations • 23 Dec 2013 • Sho Sonoda, Noboru Murata
A new initialization method for hidden parameters in a neural network is proposed.