Shinhyun Choi, Scott Tan, Yunjo Kim, and Jeehwan Kim

Massachusetts Institute of Technology

Abstract

Neuromorphic computing has recently emerged as a non-Von Neuman computing method. Because its analog switching ability to represent multiple synaptic weights by varying conductance in the vertical filaments formed in the switching medium, a memristor has been considered as a suitable neuromorphic hardware platform. Conventional memristors typically utilize an defective amorphous solid as a switching medium for defect-mediated formation of conducting filaments. However, the imperfection of the switching medium also causes stochastic filament formation leading to spatial and temporal variation of the devices. In this talk, we introduce a silicon-based epitaxial random access memory (epiRAM), where we precisely confined the conducting paths in the single-crystalline films resulting in unprecedented device performances. MIT’s epiRAM exhibits extremely low temporal/spatial variation, linear synaptic weight update, high on/off ratio (250 for analog/10,000 for digital), great endurance (>10⁹), long retention time (2 days at 85^oC), and self-selectivity. This will allow large-scale neural network hardware, paving the way for computing beyond the conventional von Neumann architecture.