Practical methods of optimization; (2nd ed.)
Practical methods of optimization; (2nd ed.)
An introduction to numerical computations (2nd ed.)
An introduction to numerical computations (2nd ed.)
Neural computing: theory and practice
Neural computing: theory and practice
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Modern heuristic techniques for combinatorial problems
Modern heuristic techniques for combinatorial problems
Minimisation methods for training feedforward neural networks
Neural Networks
Flexible data parallel training of neural networks using MIMD-Computers
PDP '95 Proceedings of the 3rd Euromicro Workshop on Parallel and Distributed Processing
Fast parallel off-line training of multilayer perceptrons
IEEE Transactions on Neural Networks
Adaptive self-scaling non-monotone BFGS training algorithm for recurrent neural networks
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Fuzzy wavelet neural network models for prediction and identification of dynamical systems
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
A new neural network training algorithm whichoptimises performance in relation to the availablememory is described. Numerically it has equivalentproperties to Full Memory BFGS optimisation (FM) whenthere are no restrictions on memory and to FM withperiodic reset when memory is limited. Achievableperformance is determined by the ratio betweenavailable memory and problem size and accordinglyvaries between that of the full and memory-lessversions of the BFGS algorithm.