Accuracy versus complexity in RBF neural networks

IEEE Instrumentation and Measurement Magazine

Volumn 4, Issue 1, 2001, Pages 32-36

  Alippi, Cesare ^b   Piuri, Vincenzo ^b   Scotti, Fabio ^b  

^a POLITECNICO DI MILANO   (Italy)

^b NONE

Author keywords

[No Author keywords available]

Indexed keywords

CAMERAS; CHARGE COUPLED DEVICES; DEFORMATION; IMAGE PROCESSING; NEURAL NETWORKS; RAILROAD TRACKS; SENSORS; WEAR OF MATERIALS;

AUTOMATIC VIDEO INSPECTION; VIRTUAL SENSOR;

RADIAL BASIS FUNCTION NETWORKS;

EID: 0035280168     PISSN: 10946969     EISSN: None     Source Type: Journal    
DOI: 10.1109/5289.911171     Document Type: Article

References (23)

1. Topological minimisation of multi-layered feed-forward neural networks by spectral decomposition
2. Composite real-time image processing for railways track profile measurement
3. New trends in intelligent system design for embedded and measurement applications
4. Towards optimally distributed computation
5. Regularization theory and neural networks architectures
6. Structural risk minimization for character recognition
7. Second order derivative for network pruning: Optimal brain surgeon
8. A simple weight decay can improve generalisation
9. Optimal brain damage
10. Using radial basis function to approximate a function end its error bounds
11. Fast pruning using principal components
12. Regularisation in the selection of radial basis function centres
13. Complete and partial fault tolerance of feed forwards neural nets
14. Fault-tolerant design of neural networks for solving optimisation problems
15. The effective dimension of the space of hidden units
16. Configurable computing
17. Design tools for embedded systems