Hybrid three-dimensional integrated circuits: A viable solution for high efficiency Neuromorphic Computing

Abstract

This work details how a neuromorphic system is simulated with a 3D integrated electronic system. The neural system is modeled as a 3D integrated circuit to investigate a highly efficient neuromorphic computing system that ameliorates implementation issues induced by prior 2D circuital systems. A 3D neuronal model incorporating the Through Silicon Via (TSV) is constructed and the performance is simulated. We maintain this work is a competent potential foundation towards a practical design methodology for producing 3D Neuromorphic Computing (NC) circuits and systems that function with lower power consumption, reduced delay, and more advanced system volumetric miniaturization than contemporary systems provide.