|
| << vorige | volgende >> |
Tijdschrift beschrijving
Alle jaargangen van het bijbehorende tijdschrift
Alle afleveringen van het bijbehorende jaargang
Alle artikelen van de bijbehorende aflevering
Details van artikel 20 van 49 gevonden artikelen
| Titel: |
Digital Hardware Implementation of a Neural System Used for Nonlinear Adaptive Prediction |
| Auteur: |
Hassène Faiedh Chokri Souani Kamel Besbes Kholdoun Torki |
| Verschenen in: |
Journal of computer science |
| Paginering: | Jaargang 2 (2006) nr. 4 pagina's 355-362 |
| Jaar: |
2006 |
| Inhoud: |
Neural networks have been widely used for many applications in digital communications.They are able to give solutions to complex problems due to their nonlinear processing and theirlearning and generalization. Neural networks are one of the key technologies for the communicationdomain and accordingly a special effort may be expected to be paid to real time hardwareimplementation issues. In this study, it is proposed a digital hardware implementation of a neuralsystem based on a multilayer perceptron (MLP). The neural system is used for the nonlinear adaptiveprediction of nonstationary signals such as speech signals. The implemented architecture of the MLP isgenerated using a generic elementary neuron (EN). The polynomial approximation method is used toimplement the sigmoidal activation function. The back-propagation algorithm is used to implant theprediction task. The circuit implementation architecture is detailed, for achieving real-time predictionfor speech signals. The designed ASIC circuit includes a neural network block, an on-chip learningblock and a memory used for storing the synaptic weights for updating. |
| Uitgever: |
Science Publications (provided by DOAJ) |
| Bronbestand: |
Elektronische Wetenschappelijke Tijdschriften |
Details van artikel 20 van 49 gevonden artikelen
| << vorige | volgende >> |