An enhanced training algorithm for multilayer neural networks based on reference output of hidden layer

Neural Computing and Applications

Volumn 8, Issue 3, 1999, Pages 218-225

  Li, Y ^a   Rad, A B ^a   Peng, W ^b  

^a HONG KONG POLYTECHNIC UNIVERSITY   (Hong Kong)

^b FLINDERS UNIVERSITY   (Australia)

Author keywords

Backpropagation; BFGS Quasi Newton algorithm; Conjugate gradient algorithm; Least squares; Multilayer neural networks

Indexed keywords

EID: 0033240932     PISSN: 09410643     EISSN: None     Source Type: Journal    
DOI: 10.1007/s005210050024     Document Type: Article

References (15)

1. Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error propagation in parallel distributed processing. In: DE Rumelhart, JL McClelland, eds., Explorations in the Microstructures of Cognition, Vol. 1. Foundations, MIT Press, Cambridge, MA, 1986; 318-362
2. Battiti R. Accelerating backpropagation learning, two optimisation methods. Complex System 1989; 3: 331-342
3. Yam YF, Chow TWS. Extended backpropagation algorithm. Electr Lett 1993; 29(9): 1701-1702
4. Humpert BK. Improving backpropagation with a new error function. Neural Networks 1994; 7(8): 1191-1192
5. Van Ooyen A, Nienhuis B. Improving the convergence of the backpropagation algorithm. Neural Networks 1992; 5: 465-471
6. Kinnebrock W. Accelerating the standard backpropagation method using genetic approach. Neurocomputing 1994; 13: 583-588
7. Zhang B, Zhang L, Wu F. Programming based learning algorithms of neural networks with self-feedback connections. IEEE Trans Neural Networks 1995; 6(3): 771-778
8. Konig FB, Barmann F. A learning algorithm for multilayered neural networks based on linear least square problems. Neural Networks 1993; 6: 127-131
9. Konig FB, Barmann F. On a class of efficient learning algorithms for neural networks. Neural Networks 1992; 5: 139-144
10. Coetzee FM, Stonick VL. Topology and geometry of single hidden layer network least squares weight solutions. Neural Computation 1995; 7: 672-705
11. Ergezinger S, Thomsn E. An accelerated learning algorithm for multilayer perceptrons: Optimisation layer by layer. IEEE Trans Neural Networks 1995; 6(1): 31-42
12. Cybenko G. Approximation by superposition of a sigmoidal function. Math. Control Signals Syst 1989; 2: 303-314
13. Dorf RC, Bishop HR. Modern Control System. Addison-Wesley, 1995
14. Demuth H, Beale M. Neural network Toolbox for use with MATLAB. The Matlab Works, Inc., January 1998 pp 5-20-5-40
15. Li Y, Rad AB. A cascading structure and training method for multi-layer neural networks. Int J Neural Systems 1997; 8(5/6): 509-515