Multigradient: A new neural network learning algorithm for pattern classification

IEEE Transactions on Geoscience and Remote Sensing

Volumn 39, Issue 5, 2001, Pages 986-993

  Go, Jinwook ^b   Han, Gunhee ^b   Kim, Hagbae ^a,b   Lee, Chulhee ^a,b  

^a Yonsei University ^*

^b Yonsei University   (South Korea)

Author keywords

Backpropagation; Gradient; Learning algorithm; Multilayer feedforward neural networks; Multispectral data; Pattern classification

Indexed keywords

BACKPROPAGATION; CONVERGENCE OF NUMERICAL METHODS; FEEDFORWARD NEURAL NETWORKS; LEARNING ALGORITHMS; MULTILAYER NEURAL NETWORKS;

BACKPROPAGATION LEARNING ALGORITHM; MULTILAYER FEEDFORWARD NEURAL NETWORKS; MULTISPECTRAL DATA;

PATTERN RECOGNITION;

EID: 0035331624     PISSN: 01962892     EISSN: None     Source Type: Journal    
DOI: 10.1109/36.921416     Document Type: Article

References (22)

1. Handwritten alphanumeric character recognition by the neocognitron
2. Parallel consensual neural networks
3. A neural-statistical approach to multitemporal and multisource remote-sensing image classification
4. Finding optimal neural networks for land use classification
5. Application of multilayer feedforward neural networks to precipitation cell-top altitude estimation
6. A neural network algorithm for sea ice edge classification
7. The past, present, and future of neural networks for signal processing
8. Decision boundary feature extraction for neural networks
9. A neural-network approach to radiometric sensing of land-surface parameters
10. Classification of multisource and hyperspectral data based on decision fusion
11. Classification and feature extraction of AVIRIS data
12. Classification accuracy improvement of neural network classifiers by using unlabeled data
13. Accelerating the convergence of the back-propagation method
14. Increased rates of convergence through learning rate adaptation
15. Dynamic learning rate optimization of the backpropagation algorithm
16. Fast second order learning algorithms for feedforward multilayer neural networks and its applications
17. First- and second order methods for learning: Between steepest descent and Newton's method
18. A scaled conjugate gradient algorithm for fast supervised learning
19. Training feedforward networks with the Marquardt algorithm
20. An introduction to computing with neural nets
21. A crops and soils data base for scene radiation research