1S1R-Based Stable Learning through Single-Spike-Encoded Spike-Timing-Dependent Plasticity

Abstract

Spike-timing-dependent plasticity (STDP) is emerging as a simple and biologically-plausible approach to learning, and specialized digital implementations are readily available. Memristor technology has been embraced as a much denser solution than digital static random-access memory (SRAM) implementations of STDP synapses, with plasticity capabilities built into the physics of these devices. One-selector-one-memristor (1S1R) arrays using volatile memristor devices as selectors are capable of the desired synaptic behavior using efficient spike-events, but previous literature has only explored the dynamics of single 1S1R synapses, or groups of synapses for single neurons. When placed in the context of an SNN, unintentional synapse disturbances are revealed that must be addressed. We present 1 a technique for STDP-based learning, enabled for dense 1S1R technology and utilizing efficient single-spike encoding. This technique leverages the array's dynamics to produce models that are stable, resilient to noise, and power-efficient.

Study on sneak path effect in self-rectifying crossbar arrays based on emerging memristive devices

“…In recent works, the memristive crossbar arrays (MCA) are intensively studied with various typologies and different applications: 1-transistor-1-resistor (1T1R) (Li et al, 2018;Yao et al, 2020), 1-selector-1-resistor (1S1R) (Taylor et al, 2021), and 1-resistor (1R). In comparison to the 1T1R and 1S1R crossbar typologies, the 1R passive crossbar topology utilizes the self-rectifying switching behavior of the individual memristive cell to maintain its operational performance rather than relying on external devices, such as transistors and selectors that cause more power consumption (Li and Xia, 2019).…”