10 citations · 13 across the 6 of their papers we have counts for
8 papers
Practical Insights of Repairing Model Problems on Image Classification
Akihito Yoshii, Susumu Tokumoto, Fuyuki Ishikawa
Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is…
NeuRecover: Regression-Controlled Repair of Deep Neural Networks with Training History
Shogo Tokui, Susumu Tokumoto, Akihito Yoshii +4
Systematic techniques to improve quality of deep neural networks (DNNs) are critical given the increasing demand for practical applications including safety-critical ones. The key…
Robustifying Controller Specifications of Cyber-Physical Systems Against Perceptual Uncertainty
Tsutomu Kobayashi, Rick Salay, Ichiro Hasuo +3
Formal reasoning on the safety of controller systems interacting with plants is complex because developers need to specify behavior while taking into account perceptual uncertainty…
Architecture-Guided Test Resource Allocation Via Logic
Clovis Eberhart, Akihisa Yamada, Stefan Klikovits +4
We introduce a new logic named Quantitative Confidence Logic (QCL) that quantifies the level of confidence one has in the conclusion of a proof. By translating a fault tree represe…
A Mutation-based Approach for Assessing Weight Coverage of a Path Planner
Thomas Laurent, Paolo Arcaini, Fuyuki Ishikawa +1
Autonomous cars are subjected to several different kind of inputs (other cars, road structure, etc.) and, therefore, testing the car under all possible conditions is impossible. To…
Adapting SQuaRE for Quality Assessment of Artificial Intelligence Systems
Hiroshi Kuwajima, Fuyuki Ishikawa
More and more software practitioners are tackling towards industrial applications of artificial intelligence (AI) systems, especially those based on machine learning (ML). However,…