Mm. Ahmed et al., HIERARCHICAL ANALOG BEHAVIORAL MODELING OF ARTIFICIAL NEURAL NETWORKS, Analog integrated circuits and signal processing, 16(2), 1998, pp. 121-139
A hierarchical methodology for analog behavioral modeling of the basic
building blocks of neural networks is presented using HDL-A.(1) This
hierarchy is formed of three levels in order to satisfy the different
requirements of the CAD tools which may incorporate the models. The pr
esented models include all the nonidealities present in the actual cir
cuit in addition to being flexible and consuming shorter simulation ti
me. This improvement in simulation time is verified through examples a
t both the circuit and system levels.