Hardware calibrated learning to compensate heterogeneity in analog RRAM-based Spiking Neural Networks
This addresses the problem of hardware heterogeneity for low-power neuromorphic computing, representing an incremental improvement in calibration techniques.
The authors tackled the challenge of variability in analog RRAM-based Spiking Neural Networks by proposing a Neuromorphic Hardware Calibrated SNN that self-corrects hardware non-idealities, achieving high accuracy on benchmark tasks.
Spiking Neural Networks (SNNs) can unleash the full power of analog Resistive Random Access Memories (RRAMs) based circuits for low power signal processing. Their inherent computational sparsity naturally results in energy efficiency benefits. The main challenge implementing robust SNNs is the intrinsic variability (heterogeneity) of both analog CMOS circuits and RRAM technology. In this work, we assessed the performance and variability of RRAM-based neuromorphic circuits that were designed and fabricated using a 130\,nm technology node. Based on these results, we propose a Neuromorphic Hardware Calibrated (NHC) SNN, where the learning circuits are calibrated on the measured data. We show that by taking into account the measured heterogeneity characteristics in the off-chip learning phase, the NHC SNN self-corrects its hardware non-idealities and learns to solve benchmark tasks with high accuracy. This work demonstrates how to cope with the heterogeneity of neurons and synapses for increasing classification accuracy in temporal tasks.