In this paper a neurocomputing strategy is presented which combines data processing capabilities of neural networks and numerical structural optimization. In this strategy, an improved counterpropagation neural network is used. Two arti"cial neural networks are trained, one for the constraints and t
β¦ LIBER β¦
Inversion of neural networks by gradient descent
β Scribed by J Kindermann; A Linden
- Publisher
- Elsevier Science
- Year
- 1990
- Tongue
- English
- Weight
- 536 KB
- Volume
- 14
- Category
- Article
- ISSN
- 0167-8191
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
Structural optimization by gradient-base
β
A. Iranmanesh; A. Kaveh
π
Article
π
1999
π
John Wiley and Sons
π
English
β 141 KB
π 2 views
Approximation of inverse system (many-va
β
Masakazu Shinki; Kiyotaka Shimizu
π
Article
π
2001
π
John Wiley and Sons
π
English
β 289 KB
Convergence analysis of online gradient
β
Wei Wu; Jian Wang; Mingsong Cheng; Zhengxue Li
π
Article
π
2011
π
Elsevier Science
π
English
β 297 KB
This paper considers a class of online gradient learning methods for backpropagation (BP) neural networks with a single hidden layer. We assume that in each training cycle, each sample in the training set is supplied in a stochastic order to the network exactly once. It is interesting that these sto
Optimization of operating conditions for
β
O. CortΓ©s; G. Urquiza; J.A. HernΓ‘ndez
π
Article
π
2009
π
Elsevier Science
π
English
β 628 KB
Stability, robustness and approximation
β
E. B. Kosmatopoulos; M. A. Christodoulou
π
Article
π
1994
π
John Wiley and Sons
π
English
β 690 KB
Simulation of membrane separation by neu
β
Harri Niemi; Abhay Bulsari; Seppo Palosaari
π
Article
π
1995
π
Elsevier Science
π
English
β 501 KB