Search Results for author: Masaki Waga

Found 10 papers, 5 papers with code

Probabilistic Black-Box Checking via Active MDP Learning

no code implementations15 Jul 2023 Junya Shijubo, Masaki Waga, Kohei Suenaga

Our method, ProbBBC, refines the conventional BBC approach by (1) employing an active Markov Decision Process (MDP) learning method during the learning phase, (2) incorporating probabilistic model checking in the synthesis phase, and (3) applying statistical hypothesis testing in the validation phase.

BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models

no code implementations31 Oct 2022 Atsushi Kikuchi, Kotaro Uchida, Masaki Waga, Kohei Suenaga

We propose a new black-box method BOREx (Bayesian Optimization for Refinement of visual model Explanation) to refine a heat map produced by any method.

Bayesian Optimization Classification +2

Dynamic Shielding for Reinforcement Learning in Black-Box Environments

no code implementations27 Jul 2022 Masaki Waga, Ezequiel Castellano, Sasinee Pruekprasert, Stefan Klikovits, Toru Takisaka, Ichiro Hasuo

The dynamic shielding technique constructs an approximate system model in parallel with RL using a variant of the RPNI algorithm and suppresses undesired explorations due to the shield constructed from the learned model.

reinforcement-learning Reinforcement Learning (RL)

Model-bounded monitoring of hybrid systems

no code implementations15 Feb 2021 Masaki Waga, Étienne André, Ichiro Hasuo

Monitoring of hybrid systems attracts both scientific and practical attention.

Genetic Algorithm for the Weight Maximization Problem on Weighted Automata

1 code implementation11 Apr 2020 Elena Gutiérrez, Takamasa Okudono, Masaki Waga, Ichiro Hasuo

In this work, we propose, implement and evaluate a metaheuristic based on genetic algorithms to approximate solutions to the WMP.

Online Quantitative Timed Pattern Matching with Semiring-Valued Weighted Automata

1 code implementation28 Jun 2019 Masaki Waga

This is the first quantitative and online timed pattern matching algorithm to the best of our knowledge.

Formal Languages and Automata Theory

Symbolic Monitoring against Specifications Parametric in Time and Data

1 code implementation11 May 2019 Masaki Waga, Étienne André, Ichiro Hasuo

Monitoring consists in deciding whether a log meets a given specification.

Formal Languages and Automata Theory Systems and Control

Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces

no code implementations5 Apr 2019 Takamasa Okudono, Masaki Waga, Taro Sekiyama, Ichiro Hasuo

We present a method to extract a weighted finite automaton (WFA) from a recurrent neural network (RNN).

regression

Online Parametric Timed Pattern Matching with Automata-Based Skipping

1 code implementation18 Mar 2019 Masaki Waga, Étienne André

Timed pattern matching has strong connections with monitoring real-time systems.

Formal Languages and Automata Theory

Offline timed pattern matching under uncertainty

1 code implementation21 Dec 2018 Étienne André, Ichiro Hasuo, Masaki Waga

Given a log and a specification, timed pattern matching aims at exhibiting for which start and end dates a specification holds on that log.

Systems and Control Logic in Computer Science F.4

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