Self-scaled conjugate gradient training algorithms
β Scribed by A.E. Kostopoulos; T.N. Grapsa
- Book ID
- 113816295
- Publisher
- Elsevier Science
- Year
- 2009
- Tongue
- English
- Weight
- 912 KB
- Volume
- 72
- Category
- Article
- ISSN
- 0925-2312
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
Through the introduction of multiple two parameter pairs of scaling factors, a modified formulation of the conjugate gradient scheme is derived. The individual pairs are separately assigned to the various substructure of a model so as to gauge the optimal local search direction and length. During th
A supervised learning algorithm (Scaled Conjugate Gradient, SCG) is introduced TIw pelformance of SCG is benchmarked against that of the standard back propagation algorithm (BP) ( Rumelhart. Hinton. & 14"illiams. 1986 ), the conjugate gradient algorithm with line search ( CGL ) ( Johansson, Dowla. &