[ The Types Forum (announcements only), http://lists.seas.upenn.edu/mailman/listinfo/types-announce ]
(Sorry for cross posting.) We are currently looking for a postdoctoral researcher to work on the "CyPhAI: Formal Analysis and Design of AI-intensive Cyber-Physical Systems" project funded by JST in Kyoto, Japan. The successful candidate will be collaborating with us on establishing mathematically-solid methodologies to model, verify, test, monitor, and control a cyber-physical system in which AI plays a crucial role. This project involves working closely with a team in Tokyo led by Masako Kishida (NII) and a team in France led by Thao Dang (CNRS). The detail of the call can be found here: https://urldefense.com/v3/__https://www.kyoto-u.ac.jp/sites/default/files/acceptance_teacher/2023-02/20230208_0858_e-f67e82e5e49b6b9c49c3eaa70e2bf5a4.pdf__;!!IBzWLUs!QUeqOFxyvhc7vUCd7LIHTzOlABQ_46gYcaOkpZMuhj-QQX640MmDSOPIO21A6zJgJj_PvuWQBEY9pxWg43oNabB5iq8IlJ9uiv4BZgszbuEUkg$ The expected research topics include testing and verifying AI-CPS using machine learning [3,6,7], secure monitoring techniques using homomorphic encryption [5], application of model checking and program logics for AI-CPS [2,4], and interpretability of machine-learned components AI-CPS [1,8], among others. The initial contract will run until the end of March 2024, with the possibility of annual renewal at maximum until March 2026. We welcome researchers on topics not listed above. If you are interested in this position, please follow the link to the detailed call for applications provided below. If you have any questions, please don't hesitate to contact us! [1] Yuhki Hatakeyama, Hiroki Sakuma, Yoshinori Konishi, Kohei Suenaga: Visualizing Color-Wise Saliency of Black-Box Image Classification Models. ACCV (3) 2020: 189-205 [2] Kohei Suenaga, Takuya Ishizawa: Generalized Property-Directed Reachability for Hybrid Systems. VMCAI 2020: 293-313 [3] Junya Shijubo, Masaki Waga, Kohei Suenaga: Efficient Black-Box Checking via Model Checking with Strengthened Specifications. RV 2021: 100-120 [4] Yusuke Kawamoto, Tetsuya Sato, Kohei Suenaga: Formalizing Statistical Beliefs in Hypothesis Testing Using Program Logic. KR 2021: 411-421 [5] Ryotaro Banno, Kotaro Matsuoka, Naoki Matsumoto, Song Bian, Masaki Waga, Kohei Suenaga: Oblivious Online Monitoring for Safety LTL Specification via Fully Homomorphic Encryption. CAV (1) 2022: 447-468 [6] Amit Gurung, Masaki Waga, Kohei Suenaga: Learning nonlinear hybrid automata from input-output time-series data. CoRR abs/2301.03915 (2023) [7] Masaki Waga, Ezequiel Castellano, Sasinee Pruekprasert, Stefan Klikovits, Toru Takisaka, Ichiro Hasuo: Dynamic Shielding for Reinforcement Learning in Black-Box Environments. ATVA 2022: 25-41 [8] Atsushi Kikuchi, Kotaro Uchida, Masaki Waga, Kohei Suenaga: BOREx: Bayesian-Optimization-Based Refinement of Saliency Map for Image- and Video-Classification Models. CoRR abs/2210.17130 (2022) -- Kohei Suenaga (末永幸平), Ph.D Associate professor (准教授) Graduate School of Informatics, Kyoto University (京都大学情報学研究科) ksuen...@gmail.com https://urldefense.com/v3/__http://www.fos.kuis.kyoto-u.ac.jp/*ksuenaga/__;fg!!IBzWLUs!QUeqOFxyvhc7vUCd7LIHTzOlABQ_46gYcaOkpZMuhj-QQX640MmDSOPIO21A6zJgJj_PvuWQBEY9pxWg43oNabB5iq8IlJ9uiv4BZgsK9maEPQ$