Abstract
Through a simulation of the tracking method for a neural network weight change on a 2D plane, we noticed that in some cases it was hard for untrained users to observe the neural network weight performance. To overcome this problem, we applied a transformation of the neural network weight trajectories on a 2D plane to the direct controller of a learning-type neural network. The simulation results confirmed that if the trajectory of the neural network weight change on a 2D plane had a simple structure, we could easily determine whether the learning of the neural network had terminated or not. However, if it had a more complex structure, we could not make this determination. The proposed transformation of the neural network weight trajectories to one-dimensional values will be useful for such cases.
Similar content being viewed by others
References
Yamada T (2005) Remarks on a tracking method of neural network weight change for a learning-type neural network direct controller. Proceedings of AROB 10th’ 05 (10th International Symposium on Artificial Life and Robotics 2005), pp 624–627
Yamada T (2006) Remarks on a tracking method of neural network weight change for adaptive type neural network direct controller. Proceedings of AROB 11th’ 06 (11th International Symposium on Artificial Life and Robotics 2006), GS19-3
Yamada T (2008) Remarks on a tracking method of neural network weight change for adaptive type neural network feed-forward feedback controller. Proceeding of AROB 13th’ 08 (13th International Symposium on Artificial Life and Robotics), pp 559–562
Yamada T (2009) Remarks on a tracking method of neural network weight change for learning type neural network feed forward feedback controller. Proceeding of AROB 14th’ 09 (14th International Symposium on Artificial Life and Robotics), pp 389–392
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the 15th International Symposium on Artificial Life and Robotics, Oita, Japan, February 4–6, 2010
About this article
Cite this article
Yamada, T. Transformation of neural network weight trajectories on a 2D plane for a learning-type neural network direct controller. Artif Life Robotics 15, 413–416 (2010). https://doi.org/10.1007/s10015-010-0832-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-010-0832-5