Name:
Daisuke URAGAMI
E-mail:
uragami.daisuke[at]nihon-u.ac.jp
Current position:
Professor, Department of Mathematical Information Engineering, College of Industrial Technology, Nihon University, Chiba, Japan
Education:
Ph. D., Doctoral Program in Information Media Science, Graduate School of Science and Technology, Kobe University
(Thesis Supervisor: Yukio-Pegio Gunji)
Research Field:
Complex and Intelligent Systems, Lattice Theory, Cellular Automata, Reinforcement Learning, Internal Measurement
Research Introduction:
I have been working on three main research topics. The first is the application of lattice theory to complex systems and intelligent systems [1, 2]. The second is the study of cellular automata [1, 3, 4]. I proposed a reservoir computing system using the asynchronous cellular automata introduced by Gunji [4]. The third is research on reinforcement learning. I have incorporated human cognitive biases and sociality into reinforcement learning systems [5, 6, 7]. In addition, I am interested in the interdisciplinary area between science and philosophy, including concepts such as Internal Measurement and Natural Born Intelligence. Recently, I have been focusing on rough set lattices, also proposed by Gunji, and exploring their application to machine learning in order to better understand complex and intelligent systems.
Selected Publications:
[1] Uragami, D., and Gunji, Y.-P., Lattice-Driven Cellular Automata implementing Local Semantics, Physica D 237, 187-197, 2008.
[2] Uragami, D., and Ohta, H., Multilayered neural network with structural lateral inhibition for incremental learning and conceptualization, BioSystems 118, 8–16, 2014.
[3] Uragami, D., Gunji, Y.-P., Universal Emergence of 1/f Noise in Asynchronously Tuned Elementary Cellular Automata, Complex Systems 27(4), 399-414, 2018.
[4] Uragami, D., Gunji, Y.-P., Universal Criticality in Reservoir Computing Using Asynchronous Cellular Automata, Complex Systems 31(1), 103-121, 2022.
[5] Uragami, D., Takahashi, T. and Matsuo, Y., Cognitively inspired reinforcement learning architecture and its application to giant-swing motion control, BioSystems 116, 1– 9, 2014.
[6] Uragami, D., Kohno, Y., Takahashi, T., Robotic Action Acquisition with Cognitive Biases in Coarse-grained State Space, BioSystems 145, 41-52, 2016.
[7] Uragami, D., Sonota, N., Takahashi, T., Social satisficing: Multi-agent reinforcement learning with satisficing agents, BioSystems 243, 105276, 2024.