CDMA and TDMA Based Neural Nets

Juan Carlos Herrero

One of the main problems in neural net implementation is how to take the information from the processing units where it is generated to other processing units, in order for the net to carry on the computation and eventually yield a result. This problem is significant enough to influence the whole physical design, thus we find a wide choice of solutions. This paper's two proposals come from the rising field of wireless communications: CDMA and TDMA. Both principles were established long time ago, but they have acquired a renewed presence due to the rapidly increasing mobile phones demand. We are going to see how CDMA and TDMA could apply to neural nets, by means of currently available technology, if we give up the concept ?connection? between units and grasp the concept ?messages? exchanged between them, to open the door to neural nets with higher number of processing units and flexible configuration.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: