Neuro-fuzzy hybrid hardware implementation with neural chip URAN
Il Song Han · 1994
This paper describes a neuro-fuzzy hardware implementation with the circuit of analogue and digital mixed operation. The circuits are suggested for membership function, MIN function and normalization function using either linear voltage-controlled MOSFET resistance or pulse stream operation. The analogue-digital hybrid way of implementation is extensible to the fuzzy-neural network as its basic configurations are already used in URAN-I of 135424 synaptic connections.>