479 citations · 1.1k across the 8 of their papers we have counts for
8 papers
Notes on Applicability of Explainable AI Methods to Machine Learning Models Using Features Extracted by Persistent Homology
Naofumi Hama
Data analysis that uses the output of topological data analysis as input for machine learning algorithms has been the subject of extensive research. This approach offers a means of…
Model free variable importance for high dimensional data
Naofumi Hama, Masayoshi Mase, Art B. Owen
A model-agnostic variable importance method can be used with arbitrary prediction functions. Here we present some model-free methods that do not require access to the prediction fu…
Deletion and Insertion Tests in Regression Models
Naofumi Hama, Masayoshi Mase, Art B. Owen
A basic task in explainable AI (XAI) is to identify the most important features behind a prediction made by a black box function . The insertion and deletion tests of Petsiuk et…
Supersymmetric Rényi Entropy in Five Dimensions
Naofumi Hama, Tatsuma Nishioka, Tomonori Ugajin
We introduce supersymmetric Rényi entropies for supersymmetric gauge theories in five dimensions. The matrix model representation is obtained using the localization…
AGT relation in the light asymptotic limit
Naofumi Hama, Kazuo Hosomichi
It is known that the path integral of correlators in Liouville theory reduces to a finite dimensional integral in the limit of vanishing coupling b. We take the example of four-poi…
Seiberg-Witten Theories on Ellipsoids
Naofumi Hama, Kazuo Hosomichi
We present a set of equations for a 4D Killing spinor which guarantees the Seiberg-Witten theories on a curved background to be supersymmetric. The equations involve an SU(2) gauge…