Measuring Information Transfer in Online Adaptation Process of Recurrent Neural Networks
p. 33-41
Abstract
In this paper, we propose a simple model that focuses on the adaptation process of an agent to an unknown system in an online manner. The agent is equipped with a recurrent neural network, and by controlling the dynamics of the interacting system, it should predict its state in one-step prediction. To quantitatively characterize the interaction modality between the agent and the interacting system, we used transfer entropy. As a result, by varying the nonlinear parameter of the interacting system and the coupling strength, we numerically show that the adaptation dynamics can be distinguished between an agent-driven and a non-agent-driven dynamics.
Index
Text
References
Bibliographical reference
Kohei Nakajima, « Measuring Information Transfer in Online Adaptation Process of Recurrent Neural Networks », CASYS, 24 | 2010, 33-41.
Electronic reference
Kohei Nakajima, « Measuring Information Transfer in Online Adaptation Process of Recurrent Neural Networks », CASYS [Online], 24 | 2010, Online since 06 September 2024, connection on 10 January 2025. URL : http://popups.lib.uliege.be/1373-5411/index.php?id=3023
Author
Kohei Nakajima
Department of General Systems Sciences, The Graduate School of Arts and Sciences, The University of Tokyo, 3-8-1 Komaba, Tokyo 153-8902, Japan