Search Results for author: Hiroya Inakoshi

Found 2 papers, 1 papers with code

ERIC: Extracting Relations Inferred from Convolutions

no code implementations19 Oct 2020 Joe Townsend, Theodoros Kasioumis, Hiroya Inakoshi

Our main contribution is to show that the behaviour of kernels across multiple layers of a convolutional neural network can be approximated using a logic program.

DTM-based Filtrations

2 code implementations12 Nov 2018 Hirokazu Anai, Frédéric Chazal, Marc Glisse, Yuichi Ike, Hiroya Inakoshi, Raphaël Tinarrage, Yuhei Umeda

Despite strong stability properties, the persistent homology of filtrations classically used in Topological Data Analysis, such as, e. g. the Cech or Vietoris-Rips filtrations, are very sensitive to the presence of outliers in the data from which they are computed.

Computational Geometry Algebraic Topology

Cannot find the paper you are looking for? You can Submit a new open access paper.