229 citations · 277 across the 10 of their papers we have counts for
10 papers
Geometry of EM and related iterative algorithms
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 measurem…
The global optimum of shallow neural network is attained by ridgelet transform
Sho Sonoda, Isao Ishikawa, Masahiro Ikeda +4
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. A series…
Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks
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. Despite t…
Estimation of neural connections from partially observed neural spikes
Taishi Iwasaki, Hideitsu Hino, Masami Tatsuno +2
Plasticity is one of the most important properties of the nervous system, which enables animals to adjust their behavior to the ever-changing external environment. Changes in synap…
Transport Analysis of Infinitely Deep Neural Network
Sho Sonoda, Noboru Murata
We investigated the feature map inside deep neural networks (DNNs) by tracking the transport map. We are interested in the role of depth (why do DNNs perform better than shallow mo…
Double Sparse Multi-Frame Image Super Resolution
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. In multi-frame super reso…
Neural Network with Unbounded Activation Functions is Universal Approximator
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 ne…
Sparse Coding Approach for Multi-Frame Image Super Resolution
Toshiyuki Kato, Hideitsu Hino, Noboru Murata
An image super-resolution method from multiple observation of low-resolution images is proposed. The method is based on sub-pixel accuracy block matching for estimating relative di…
Nonparametric Weight Initialization of Neural Networks via Integral Representation
Sho Sonoda, Noboru Murata
A new initialization method for hidden parameters in a neural network is proposed. Derived from the integral representation of the neural network, a nonparametric probability distr…
Multiplicative Nonholonomic/Newton -like Algorithm
Toshinao Akuzawa, Noboru Murata
We construct new algorithms from scratch, which use the fourth order cumulant of stochastic variables for the cost function. The multiplicative updating rule here constructed is na…