Nanoscale electronic synapses using phase change devices

Abstract

The memory capacity, computational power, communication bandwidth, energy consumption, and physical size of the brain all tend to scale with the number of synapses, which outnumber neurons by a factor of 10,000. Although progress in cortical simulations using modern digital computers has been rapid, the essential disparity between the classical von Neumann computer architecture and the computational fabric of the nervous system makes large-scale simulations expensive, power hungry, and time consuming. Over the last three decades, CMOS-based neuromorphic implementations of “electronic cortex” have emerged as an energy efficient alternative for modeling neuronal behavior. However, the key ingredient for electronic implementation of any self-learning system—programmable, plastic Hebbian synapses scalable to biological densities—has remained elusive. We demonstrate the viability of implementing such electronic synapses using nanoscale phase change devices. We introduce novel programming schemes for modulation of device conductance to closely mimic the phenomenon of Spike Timing Dependent Plasticity (STDP) observed biologically, and verify through simulations that such plastic phase change devices should support simple correlative learning in networks of spiking neurons. Our devices, when arranged in a crossbar array architecture, could enable the development of synaptronic systems that approach the density (∼10 11 synapses per sq cm) and energy efficiency (consuming ∼1pJ per synaptic programming event) of the human brain.

Compass: A scalable simulator for an architecture for cognitive computing

“…To this end, we have pursued neuroscience [42], [43], [9], nanotechnology [3], [4], [44], [5], [6], and supercomputing [11], [12]. Building on these insights, we are marching ahead to develop and demonstrate a novel, ultra-low power, compact, modular, non-von Neumann, cognitive computing architecture, namely, TrueNorth.…”

Phase change memory (PCM) materials and devices

“…Other novel application include the use of phase change cells as synapses in neuromorphic computing (Jackson et al 2013;Jo et al 2010;Kuzum et al 2011;Rajendran et al 2013). Change in synaptic strength is assumed to be the learning mechanism in biological synapses.…”

“…Neuromorphic or brain-inspired computing requires hardware components that function like brain components, and a PCM cell is a potential candidate for fulfi lling synaptic functions. PCM cell switching, that mimics spike-timing dependent plasticity, has been indeed implemented in PCM cells using a special programming scheme (Jackson et al 2013;Kuzum et al 2011). Scalable CMOS integration schemes for implementing neuromorphic computing have also been proposed ).…”

Image Edge Detection Based on Swarm Intelligence Using Memristive Networks

“…Bio-inspired computing has attracted a wide range of interest in the past few years for solving class of problems that are not well suited in von-Neumann architectures [1][2][3][4][5][6]. Implementation of such biological systems in standard Complementary Metal Oxide Semiconductor (CMOS) devices has turned out be energy inefficient; the inefficiencies stem from both CMOS devices and the computing platform.…”

“…In the quest to achieve comparable power consumption with those of biological counterparts, research has started in earnest to develop newer devices with characteristics similar to biological elements [1][2][3][4][5][6]. Furthermore, researchers are exploring new computing models to suit bio/neurocomputing systems.…”