Previous [ 1] [ 2] [ 3] [ 4] [ 5] [ 6] [ 7] [ 8] [ 9] [ 10]

¡@

Journal of Information Science and Engineering, Vol. 21 No. 4, pp. 721-732 (July 2005)

Geometrical Perspective on Learning Behavior*

Cheng-Yuan Liou, Jau-Chi Huang and Yen-Ting Kuo
Department of Computer Science and Information Engineering
National Taiwan University
Taipei, 106 Taiwan
E-mail: cyliou@csie.ntu.edu.tw

This paper constructs a geometrical perspective to justify the slow learning period and fast learning period during training. It plots the error surfaces and the solution spaces in the input space for a single neuron with two inputs. It records various training paths in this space using the back-propagation (BP) training algorithm [6]. It finds the relations between the learning curve and training path.

Keywords: multilayer network, back-propagation learning, neural network, momentum method, premature saturation

Full Text (¥þ¤åÀÉ) Retrieve PDF document (200507_04.pdf)

Received August 28, 2003; revised May 14, 2004; accepted January 6, 2005.
Communicated by Chin-Teng Lin.
*This paper was supported in part by the National Science Council of Taiwan, R.O.C., under project NSC 93-2213-E-002-081.