A Neural Network Structure Decomposition Based on Pruning and its Visualization Method
Atsushi Shibata, Jiajun Lu, Fangyan Dong,
and Kaoru Hirota
Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, G3-49, 4259 Nagatsuta, Midori-ku, Yokohama 226-8502, Japan
To decompose neural network structures for composite tasks, a pruning method and its visualization method are proposed. Visualization by placing the neurons on a 2D plane clarifies the structure related to each composited task. Experiments on a composite task using two tasks from a UCI dataset show that the neural network of the composite task contains more than 80% of neurons. The proposed methods target the transfer learning of robot motion, and results of an adaptation experiments are also referred.
and Kaoru Hirota, “A Neural Network Structure Decomposition Based on Pruning and its Visualization Method,” J. Adv. Comput. Intell. Intell. Inform., Vol.17, No.3, pp. 443-449, 2013.
-  K. G. Jolly, R. Sreerama Kumar, and R. Vijayakumar, “Intelligent task planning and action selection of a mobile robot in a multi-agent system through a fuzzy neural network approach,” Engineering Applications of Artificial Intelligence, Vol.23, pp. 923-933, 2010.
-  M. Okada, D. Nakamura, and Y. Nakamura, “Self-organizing Symbol Acquisition and Motion Generation based on Dynamics-based Information Processing System,” The Japanese Society for Artificial Intelligence, Vol.20, No.3, SP-A, pp. 177-186, 2005.
-  M. Shahjahn and K. Murase, “A Dynamic Node Decaying Method for Pruning Artificial Neural Networks,” IEICE Trans. Inf. and Syst., Vol.E86-D, No.4, pp. 736-751, April 2003.
-  M. Shahjahn and K. Murase, “A Pruning Algorithm for Training Cooperative Neural Network Ensembles,” IEICE Trans. Inf. and Syst., Vol.E89-D, No.3, pp. 1257-1269, March 2006.
-  S. Kikuchi and N. Nakamura, “Recurrent neural network with shortterm memory and fast structural learning method,” System and Computer in Japan, Vol.34, No.6, pp. 69-79, 2003.
-  Z. Zhang and J. Qiao, “A Node Pruning Algorithm for Feedforward Neural Network Based on Neural Complexity,” Int. Conf. on Intelligent Control and Information Processing, Dalian China, pp. 406-410, August 13-15, 2010.
-  C. B. D. J. Newman, S. Hettich, and C. Merz, “UCI Repository of Machine Learning Databases,” 1998.
-  http://www.geforce.com/hardware/technology/physx
-  N. Higa and H. Shirotsuchi, “Studies on An Algorithm for Reducing Redundant Units Based on Geometrical Approach,” The Institute of Electronics, Information and Communication Engineers, technical report, pp. 43-48, June 2002 (in Japanese).
-  http://opencv.org/
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 International License.