scispace - formally typeset
Search or ask a question

Answers from top 5 papers

More filters
Papers (5)Insight
Proceedings ArticleDOI
Nadia Nedjah, L. de Macedo Mourelle 
01 Sep 2003
16 Citations
In this paper, we propose reconfigurable, low-cost and readily available hardware architecture for an artificial neuron.
The proposed model has a low-cost hardware implementation property compared with the original neuron model.
Indeed, the activity of each neuron adapts to the range values it encodes but does not depend on other available goods.
Open accessJournal ArticleDOI
01 Sep 2002-Neural Networks
41 Citations
Overall this work illustrates how a hardware-realisable neuron model can capitalise on the unique computational capabilities of biological neurons.
The conclusions about how parameters compensate each other, developed in this study, can thus be used even without regard to the specific mathematical model describing a particular neuron or neuronal network.