20 citations · 29 across the 4 of their papers we have counts for
4 papers
Unsupposable Test-data Generation for Machine-learned Software
Naoto Sato, Hironobu Kuruma, Hideto Ogawa
As for software development by machine learning, a trained model is evaluated by using part of an existing dataset as test data. However, if data with characteristics that differ f…
Formal Verification of Decision-Tree Ensemble Model and Detection of its Violating-input-value Ranges
Naoto Sato, Hironobu Kuruma, Yuichiroh Nakagawa +1
As one type of machine-learning model, a "decision-tree ensemble model" (DTEM) is represented by a set of decision trees. A DTEM is mainly known to be valid for structured data; ho…
DeepSaucer: Unified Environment for Verifying Deep Neural Networks
Naoto Sato, Hironobu Kuruma, Masanori Kaneko +4
In recent years, a number of methods for verifying DNNs have been developed. Because the approaches of the methods differ and have their own limitations, we think that a number of…
Abstract Data Types in Event-B - An Application of Generic Instantiation
David Basin, Andreas Fürst, Thai Son Hoang +2
Integrating formal methods into industrial practice is a challenging task. Often, different kinds of expertise are required within the same development. On the one hand, there are…