Computing of temporal information in spiking neural networks with ReRAM synapses

Abstract

Resistive switching random-access memory (ReRAM) is a two-terminal device based on ion migration to induce resistance switching between a high resistance state (HRS) and a low resistance state (LRS). ReRAM is considered one of the most promising technologies for artificial synapses in brain-inspired neuromorphic computing systems.However, there is still a lack of general understanding about how to develop such a gestalt system to imitate and compete with the brain's functionality and efficiency.Spiking neural networks (SNNs) are well suited to describe the complex spatiotemporal processing inside the brain, where the energy efficiency of computation mostly relies on the spike carrying information about both space (which neuron fires) and time (when a neuron fires). This work addresses the methodology and implementation of a neuromorphic SNN system to compute the temporal information among neural spikes using ReRAM synapses capable of spike-timing dependent plasticity (STDP). The learning and recognition of spatiotemporal spike sequences are experimentally demonstrated. Our simulation study shows that it is possible to construct a multi-layer spatiotemporal computing network. Spatiotemporal computing also enables learning and detection of the trace of moving objects and mimicking of the hierarchy structure of the biological visual cortex adopting temporal-coding for fast recognition.

Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges

“…[42,307] As mentioned above, the synchronization of the firing times can be used as distributed clocks to temporarily bind several items together for processing. This gives the opportunity to use complex spatiotemporal codes and coordination schemes for computation, and there are recently several implementations based on RRAM.…”

“…This gives the opportunity to use complex spatiotemporal codes and coordination schemes for computation, and there are recently several implementations based on RRAM. [42,307] As mentioned above, the synchronization of the firing times can be used as distributed clocks to temporarily bind several items together for processing. Besides, the brain activities rely greatly on historical events while ANNs emphasize more on the current input.…”

Volatile Resistive Switching Memory Based on Ag Ion Drift/Diffusion—Part II: Compact Modeling

“…The dynamic response of the volatile RRAM enables several applications, e.g., exploiting the volatile behavior to mimic the short term plasticity of biological synapse in brain-inspired neuromorphic computing systems [39], [40]. For instance, spatiotemporal learning of spiking patterns was recently demonstrated in RRAM synapses [41], by correlating synaptic weights and spiking times in the same order [42]. However, this concept relies on capacitor-based neurons [42], which might result in large area consumption within the chip [43].…”

“…For instance, spatiotemporal learning of spiking patterns was recently demonstrated in RRAM synapses [41], by correlating synaptic weights and spiking times in the same order [42]. However, this concept relies on capacitor-based neurons [42], which might result in large area consumption within the chip [43].…”

Recent Progress in Synaptic Devices Based on 2D Materials

“…Based on the timescales of the activity variations, synaptic plasticity can be again classified into two main types: 1) short‐term synaptic plasticity (STSP), 2) long‐term synaptic plasticity (LTSP). By balancing the potentiation and depression functions of the cerebral cortex in the short term, STSP enhances the synaptic transmission in a controllable manner, realizing the temporal and spatial characteristics of neural activity . LTSP refers to the changes lasting for hours or longer .…”