Fully-connected single-layer STT-MTJ-based spiking neural network under process variability

The power, reliability and technological issues of today's memories have led to intensive research of emergent memory technologies and emerging computing paradigms. One of the most promising emerging technology solution is the Spin-Transfer-Torque Magnetic Random Access Memories (STT-MRAMs). It has the great advantage of favoring increasing system complexity and performance, while being CMOS compatible. Computation paradigms, such as neuromorphic computing, unfeasible a few years back due to technological limitations, can take profit from this technology. In this paper we investigate the effect of meaningful MTJ reliability issues on the behavior of a fully-connected, single layer, MTJ-based Spiking Neural Network designed for character recognition.