In this paper, we propose a new learning algorithm for multilayer feedforward neural networks, which converges faster and achieves a better classification accuracy than the conventional backpropagation learning algorithm for pattern classification. In the conventional backpropagation learning algorithm, weights are adjusted to reduce the error or cost function that reflects the differences between the computed and the desired outputs. In the proposed learning algorithm, we view each term of the output layer as a function of weights and adjust the weights directly so that the output neurons produce the desired outputs. Experiments with remotely sensed data show the proposed algorithm consistently performs better than the conventional backpropagation learning algorithm in terms of classification accuracy and convergence speed.
|Number of pages||8|
|Journal||IEEE Transactions on Geoscience and Remote Sensing|
|Publication status||Published - 2001 May|
Bibliographical noteFunding Information:
Manuscript received January 24, 2000; revised June 30, 2000. This work was supported in part by the Ministry of Information and Communication (MIC). The authors are with the Department of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, Korea (e-mail: firstname.lastname@example.org). Publisher Item Identifier S 0196-2892(01)03833-5.
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering
- Earth and Planetary Sciences(all)