Artigo Acesso aberto

A Real-Time Closed-Loop Setup for Hybrid Neural Networks

2007; Institute of Electrical and Electronics Engineers; Linguagem: Inglês

10.1109/iembs.2007.4352961

ISSN

1557-170X

Autores

Guilherme Bontorin, Sylvie Renaud, André Garenne, Ludovic Alvado, Gwendal Le Masson, Jean Tomas,

Tópico(s)

CCD and CMOS Imaging Sensors

Resumo

Hybrid living-artificial neural networks are an efficient and adaptable experimental support to explore the dynamics and the adaptation process of biological neural systems. We present in this paper an innovative platform performing a real-time closed-loop between a cultured neural network and an artificial processing unit like a robotic interface. The system gathers bioware, hardware, and software components and ensures the closed-loop data processing in less than 50 micros. We detail here the system components and compare its performances to a recent commercial platform.

Referência(s)