Abstract
This paper proposes a multilayer perceptron neural network (MLP) which optimizes both the matrix weights and the numbers of hidden neurons. Initially, the proposed system uses a reduced number of hidden neurons, optimizing the matrix weights by using a simultaneous perturbation algorithm. Once the network converges, its function is analyzed and if this is not as expected, a hidden neuron is added. This process is repeated until achieving the desired functioning. The results obtained show that the proposed system functions similarly to that of a conventional MLP when this has an optimal number of nodes in the hidden layer, decreasing the computational complexity during the training step.
| Translated title of the contribution | Growing cell neural network using simultaneous perturbation |
|---|---|
| Original language | Spanish |
| Pages (from-to) | 45-52 |
| Number of pages | 8 |
| Journal | Informacion Tecnologica |
| Volume | 15 |
| Issue number | 5 |
| State | Published - 2004 |