Publikācijas veids |
Publikācija RTU zinātniskajā žurnālā
|
Pamatdarbībai piesaistītais finansējums |
Nav zināms
|
Aizstāvēšana: |
, |
Publikācijas valoda |
English (en) |
Nosaukums oriģinālvalodā |
Comparative Analisys of Different Approaches Towards Multilayer Percentron Training |
Pētniecības nozare |
2. Inženierzinātnes un tehnoloģijas |
Pētniecības apakšnozare |
2.2. Elektrotehnika, elektronika, informācijas un komunikāciju tehnoloģijas |
Autori |
Aleksandrs Vališevskis
|
Atslēgas vārdi |
neural networks; time-series prediction; adaptive learning algorithms; backpropagation; QuickProp; Rprop |
Anotācija |
A comparative analysis of four multilayer perceptron learning algorithms is exposed in this work: the error
backpropagation algorithm and three other algorithms with fundamentally different approaches towards the
improvement of convergence time. Stock exchange share price prediction is at the basis of the comparison of the
algorithms. The optimal neural network topology for the solution of the above-mentioned task is determined in this
work. Furthermore the forecasts concerning four neural networks with the same topology, but trained with the help
of different algorithms are being compared. Special attention is paid to the generalisation ability of neural
networks. A series of reasons, which can cause neural network forecast delay problems, is mentioned. |
Atsauce |
Vališevskis, A. Comparative Analisys of Different Approaches Towards Multilayer Percentron Training. Datorvadības tehnoloģijas. Nr.5, 2001, 157.-167.lpp. ISSN 1407-7493. |
Pilnais teksts |
Pilnais teksts
|
ID |
11124 |