Learning Flexible Neural Networks for Pattern Recognition
Learning Flexible Neural Networks for Pattern Recognition
- New search for: A. Mirzaaghazadeh
- New search for: H. Motameni
- New search for: M. Karshenas
- New search for: H. Nematzadeh
- New search for: A. Mirzaaghazadeh
- New search for: H. Motameni
- New search for: M. Karshenas
- New search for: H. Nematzadeh
Learning the gradient of neuron's activity function like the weight of links causes a new specification which is flexibility. In flexible neural networks because of supervising and controlling the operation of neurons, all the burden of the learning is not dedicated to the weight of links, therefore in each period of learning of each neuron, in fact the gradient of their activity function, cooperate in order to achieve the goal of learning thus the number of learning will be decreased considerably. Furthermore, learning neurons parameters immunes them against changing in their inputs and factors which cause such changing. Likewise initial selecting of weights, type of activity function, selecting the initial gradient of activity function and selecting a fixed amount which is multiplied by gradient of error to calculate the weight changes and gradient of activity function, has a direct affect in convergence of network for learning.
Document information
Learning Flexible Neural Networks for Pattern Recognition
2007-09-24
oai:zenodo.org:1086271
Article (Journal)
Electronic Resource
English
| DDC: | 629 |
Similar titles
Pattern Recognition using Fourier Descriptors and Neural Networks
| British Library Conference Proceedings | 1994
Comparison between a neural networks and pattern recognition classification
| Tema Archive | 2008
Pattern Recognition in Space Physics using Hybrid Artificial Neural Networks
| British Library Conference Proceedings | 1998
Pattern recognition by homomorphic graph matching using Hopfield neural networks
| British Library Online Contents | 1995