ADAPTIVE LOGIC SYNTHESIS BY FERROELECTRIC SPIKING NEURON CIRCUITS

ABSTRACT This paper presents a complete formalism for adaptive logic synthesis using spiking neurons. The fundamental paradigm of the spiking neuron in discrete time is modified to create a taxonomy of all Boolean functions. The model is based in an extended version of the Integrate-and-Fire model using a Ferroelectric capacitors as basic units in the model. The realization of logic components such as flip flops, counters and shift registers synthesized with the Spiking FeNeuron are demonstrated. The library of logic functions allow for self-adaptive hardware synthesis and can be used for an automatic microcode generation.