20 citations · 29 across the 4 of their papers we have counts for
5 papers
Universal approximation property of invertible neural networks
Isao Ishikawa, Takeshi Teshima, Koichi Tojo +3
Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various m…
Obstructions to the existence of compact Clifford-Klein forms for tangential symmetric spaces
Koichi Tojo
For a homogeneous space of reductive type, we consider the tangential homogeneous space . In this paper, we give obstructions to the existence of compact Clifford-Kl…
Universal Approximation Property of Neural Ordinary Differential Equations
Takeshi Teshima, Koichi Tojo, Masahiro Ikeda +2
Neural ordinary differential equations (NODEs) is an invertible neural network architecture promising for its free-form Jacobian and the availability of a tractable Jacobian determ…
Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
Takeshi Teshima, Isao Ishikawa, Koichi Tojo +3
Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. However, their desirabl…
On a method to construct exponential families by representation theory
Koichi Tojo, Taro Yoshino
Exponential family plays an important role in information geometry. In arXiv:1811.01394, we introduced a method to construct an exponential family on…