Embedded Files
I am interested in research on the acquisition of human intelligence and the development of human-like intelligent robots, based on a constructivist approach.
I've developed human-like mathematical models through unsupervised learning using generative AI such as GPTs and diffusion models and statistical models. My work also included human behavior analysis, anomaly detection, multiple robot operations, imitation learning, and cooperative behavior of robots.
○Name
Masatoshi NAGANO, Ph.D.
○Name
Masatoshi NAGANO, Ph.D.
○Background:
○Background:
2025~ Assistant Professor @Kyoto University
2025~ Visiting Researcher @The University of Electro-Communications
2024~2025 Project Researcher @The University of Electro-Communications
2023-2024 Company Researcher @NTT
~2023 Student @The University of Electro-Communications
○Main works
- Masatoshi Nagano, Tomoaki Nakamura, "Unsupervised phoneme and word acquisition from continuous speech based on a hierarchical probabilistic generative model," Advanced Robotics, 37(19) 1253-1265, Sep 15, 2023.
- Masatoshi Nagano, Tomoaki Nakamura, Takayuki Nagai, Daichi Mochihashi, Ichiro Kobayashi, "Spatio-temporal categorization for first-person-view videos using a convolutional variational autoencoder and Gaussian processes," Frontiers in Robotics and AI, 9, Sep 30, 2022.
- Masatoshi Nagano, Tomoaki Nakamura, "Learning Word Meanings Using Joint Attention and MLDA in Environments with a Plurality of Objects," Journal of the Robotics Society of Japan, 39(6) 549-552, Jul, 2021.
2025~ Assistant Professor @Kyoto University
2025~ Visiting Researcher @The University of Electro-Communications
2024~2025 Project Researcher @The University of Electro-Communications
2023-2024 Company Researcher @NTT
~2023 Student @The University of Electro-Communications
○Main works
- Masatoshi Nagano, Tomoaki Nakamura, "Unsupervised phoneme and word acquisition from continuous speech based on a hierarchical probabilistic generative model," Advanced Robotics, 37(19) 1253-1265, Sep 15, 2023.
- Masatoshi Nagano, Tomoaki Nakamura, Takayuki Nagai, Daichi Mochihashi, Ichiro Kobayashi, "Spatio-temporal categorization for first-person-view videos using a convolutional variational autoencoder and Gaussian processes," Frontiers in Robotics and AI, 9, Sep 30, 2022.
- Masatoshi Nagano, Tomoaki Nakamura, "Learning Word Meanings Using Joint Attention and MLDA in Environments with a Plurality of Objects," Journal of the Robotics Society of Japan, 39(6) 549-552, Jul, 2021.
○Works
○Works
Google Scholar
○Affiliated academic society
- The Japanese Society for Artificial Intelligence
- The Robotics Society of Japan
○Funding (Very Thanks)
- Japan Society for the Promotion of Science [URL]
- Honjo International Scholarship Foundation
- Moonshot R&D [URL]
Google Scholar
○Affiliated academic society
- The Japanese Society for Artificial Intelligence
- The Robotics Society of Japan
○Funding (Very Thanks)
- Japan Society for the Promotion of Science [URL]
- Honjo International Scholarship Foundation
- Moonshot R&D [URL]
You could check the researchmap for details of my profile and work.
Page updated
Google Sites
Report abuse