ActInf GuestStream 104.1 ~ Tadahiro Taniguchi: Collective Predictive Coding and Active Inference

Tadahiro Taniguchi:
Collective Predictive Coding and Active Inference: A New Perspective on Emergent Communication

Humans have developed language (i.e., symbol) systems through adaptation to the real world and communication between agents. In recent years, large-scale language models (LLMs) have gained attention for their ability to understand and generate language through predictive learning on vast corpora. However, the computational mechanisms underlying language formation as an extension of real-world adaptation remain unclear.

In this livestream, Tadahiro Taniguchi (Kyoto University) introduces the Collective Predictive Coding (CPC) hypothesis, a computational model of symbol emergence systems and generative emergent communication. CPC posits that symbol systems arise from society-wide predictive coding, framing language emergence as decentralized Bayesian inference embodied in language games within multi-agent systems. This perspective extends the Free Energy Principle (FEP) to the societal level, offering insights into AI-human coexistence.

### References:
- Taniguchi, T. (2024). Collective predictive coding hypothesis:
Symbol emergence as decentralized Bayesian inference. Frontiers in
Robotics and AI, 11, 1353870.
https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2024.1353870/full

- Taniguchi, T., Ueda, R., Nakamura, T., Suzuki, M., & Taniguchi, A.
(2024). Generative Emergent Communication: Large Language Model is a
Collective World Model. arXiv preprint arXiv:2501.00226.
[https://arxiv.org/abs/2501.00226]

- Taniguchi, T., Takagi, S., Otsuka, J., Hayashi, Y., & Hamada, H. T.
(2024). Collective predictive coding as a model of science:
Formalizing scientific activities towards generative science. arXiv
preprint arXiv:2409.00102.
[https://arxiv.org/abs/2409.00102]

- Taniguchi, T., Hirai, Y., Suzuki, M., Murata, S., Horii, T., &
Tanaka, K. (2025). System 0/1/2/3: Quad-process theory for
multi-timescale embodied collective cognitive systems. arXiv preprint
arXiv:2503.06138.
[https://arxiv.org/abs/2503.06138]

### Bio:
Tadahiro Taniguchi received his M.E. and Ph.D. degrees from Kyoto University in 2003 and 2006, respectively. From April 2005 to March 2006, he was a Japan Society for the Promotion of Science (JSPS) Research Fellow (DC2) at the Department of Mechanical Engineering and Science, Kyoto University. He continued as a JSPS Research Fellow (PD) from April 2006 to March 2007 in the same department and from April 2007 to March 2008 at the Graduate School of Informatics, Kyoto University. From April 2008 to March 2010, he served as an Assistant Professor in the Department of Human and Computer Intelligence, Ritsumeikan University, and was promoted to Associate Professor (April 2010–March 2017). During this period, he was also a Visiting Associate Professor at Imperial College London (September 2015–September 2016). From April 2017 to March 2024, he was a Professor at Ritsumeikan University and served as a Visiting General Chief Scientist at Panasonic Holdings Corporation. Since April 2024, he has been a Professor at the Graduate School of Informatics, Kyoto University, while also holding an Affiliate Professorship at the Research Organization of Science and Technology, Ritsumeikan University. Throughout his career, Dr. Taniguchi has been deeply involved in machine learning, emergent systems, cognitive robotics, and symbol emergence, making significant contributions to these fields.

Active Inference Institute information:
Website: https://www.activeinference.institute/
Activities: https://activities.activeinference.institute/
Discord: https://discord.activeinference.institute/
Donate: http://donate.activeinference.institute/
YouTube: https://www.youtube.com/c/ActiveInference/
X: https://x.com/InferenceActive
Active Inference Livestreams: https://video.activeinference.institute/