20 citations · 59 across the 18 of their papers we have counts for
5 papers · 1 filter
Kernel Mean Embeddings of Von Neumann-Algebra-Valued Measures
Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda +2
Kernel mean embedding (KME) is a powerful tool to analyze probability measures for data, where the measures are conventionally embedded into a reproducing kernel Hilbert space (RKH…
Analysis via Orthonormal Systems in Reproducing Kernel Hilbert -Modules and Applications
Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda +3
Kernel methods have been among the most popular techniques in machine learning, where learning tasks are solved using the property of reproducing kernel Hilbert space (RKHS). In th…
Metric on random dynamical systems with vector-valued reproducing kernel Hilbert spaces
Isao Ishikawa, Akinori Tanaka, Masahiro Ikeda +1
Development of metrics for structural data-generating mechanisms is fundamental in machine learning and the related fields. In this paper, we give a general framework to construct…
Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators
Isao Ishikawa, Keisuke Fujii, Masahiro Ikeda +2
The development of a metric for structural data is a long-term problem in pattern recognition and machine learning. In this paper, we develop a general metric for comparing nonline…
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…