Anda belum login :: 05 Dec 2023 03:36 WIB
On-Line Retrainable Neural Networks : Improving The Performance Of Neural Networks in Image Analysis Problems
Doulamis, A. D.
Doulamis, N. D.
Kollias, S. D.
Article from Journal - ilmiah internasional
IEEE Transactions on Neural Networks vol. 11 no. 1 (2000)
Perpustakaan Pusat (Semanggi)
1 (dapat dipinjam: 0)
Lihat Detail Induk
A novel approach is presented in this paper for improving the performance of neural - network classifiers in image recognition, segmentation, or coding applications, based on a retraining procedure at the user level. The procedure includes : 1) a training algorithm for adapting the network weights to the current condition ; 2) a maximum a posteriori (MAP) estimation procedure for optimally selecting the most representative data of the current environment as retraining data ; and 3) a decision mechanism for determining when network retraining should be activated. The training algorithm takes into consideration both the former and the current network knowledge in order to achieve good generalization. The MAP estimation procedure models the network output as a Markov random field (MRF) and optimally selects the set of training inputs and corresponding desired outputs. Results are presented which illustrate the theoretical developments as well as the performance of the proposed approach in real - life experiments.
Klik untuk menuliskan opini Anda tentang koleksi ini!
Copyright © 2006, 2007
Unika Atma Jaya
, all rights reserved
Process time: 0.015625 second(s)