A current-mode neuro-fuzzy network
Massimo Conti, Simone Orcioni, Claudio Turchetti · 2002
A new neuro-fuzzy network based on a neural model called Approximate Identity Neural Network (AINN) is presented in this work. The ability of neural networks to learn from examples and the ability of the fuzzy model to code human knowledge can be helpfully joined to create an adaptive fuzzy system. Our architecture is particularly suited to be implemented by analogue CMOS VLSI hardware. The architecture, a circuit implementation and a simple implementation example with Spectre simulation are presented.