๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Dynamic tunneling based regularization in feedforward neural networks

โœ Scribed by Y.P. Singh; Pinaki RoyChowdhury

Publisher
Elsevier Science
Year
2001
Tongue
English
Weight
137 KB
Volume
131
Category
Article
ISSN
0004-3702

No coin nor oath required. For personal study only.

โœฆ Synopsis

This paper presents a new regularization method based on dynamic tunneling for enhancing generalization capability of multilayered neural networks. The proposed method enables escape through undesired sub-optimal solutions on the composite error surface by means of dynamic tunneling. Undesired sub-optimal solutions may be increased or introduced from regularized objective function. Hence, the proposed method is capable of enhancing the regularization property without getting stuck at sub-optimal values in search space. The regularization property and escape from the sub-optimal values have been demonstrated through computer simulations on two examples.

๐Ÿ“œ SIMILAR VOLUMES

A robot endeffector tracking system base
A robot endeffector tracking system based on feedforward neural networks
โœ Seonghyun Baek; Dong-Sun Park; Jaiwan Cho; Yong-Bum Lee ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 693 KB

In this paper, we describe a robot endeffector tracking system based on two neural networks. The designed networks are to recognize the current po~,;ition and to estimate the next position of the endeffector. This tracking system can be very useful in controlling a robot at a remote site. A multila