A low-power charge-based integrate-and-fire circuit for binarized-spiking neural network

This paper presents a charge-based integrate-and-fire (IF) circuit for in-memory binary spiking neural networks (BSNNs). The proposed IF circuit can mimic both addition and subtraction operations that permit better incorporation with in-memory XNOR-based synapses to implement the BSNN processing core. To evaluate the proposed design, we have developed a framework that incorporates the circuit's imperfections effects into the system-level simulation. The array circuits use 2T-2J Spin-Transfer-Torque Magnetoresistive RAM (STT-MRAM) based on a 65-nm commercial CMOS and a fitted magnetic tunnel junction (MTJ). The system model has been described in Pytorch to best fit the extracted parameters from circuit levels, including the cover of device nonidealities and process variations. The simulation results show that the proposed design can achieve a performance of 5.10 fJ/synapse and reaches 82.01% classification accuracy for CIFAR-10 under process variation.

Automated summary

This paper proposes a charge-based integrate-and-fire (IF) circuit for in-memory binary spiking neural networks (BSNNs). The circuit can perform addition and subtraction operations, which makes it compatible with in-memory XNOR-based synapses for implementing the BSNN processing core. A framework is developed to evaluate the circuit design by considering its imperfections effects in system-level simulation. The simulation results show that the proposed design achieves a performance of 5.10 fJ/synapse and an 82.01% classification accuracy for CIFAR-10 under process variation.