1.
Gripsy Paul Mannickathan
– Assistant Professor, Department of CSE, SOET, CMR University, Bangalore, Karnataka, India.
2.
Yeldo K. Varghese
– UG Scholar, Department of CSE, ASIET, APJ KTU, Kerala, India.
3.
Sahala Mariyam P. S.
– UG Scholar, Department of CSE, ASIET, APJ KTU, Kerala, India.
4.
Nimal K. G.
– UG Scholar, Department of CSE, ASIET, APJ KTU, Kerala, India.
5.
Pavithra S.
– UG Scholar, Department of CSE, ASIET, APJ KTU, Kerala, India.
6.
Noel Sabu
– UG Scholar, Department of CSE, ASIET, APJ KTU, Kerala, India.
Received 10-Jun-2026
Accepted 15-Jun-2026
Published 22-Jun-2026
Abstract
Spiking Neural Networks (SNNs) represent a biologically grounded computational paradigm in which information is carried by discrete spike events, conferring structural compatibility with low-power, event-driven neuromorphic hardware. A persistent impediment to realising the full energy benefit of SNNs in practice is the near-universal adoption of fixed firing thresholds, which prevent individual neurons from self-regulating their activity and permit task-irrelevant spike generation to accumulate unchecked. This paper introduces and evaluates a Homeostatically Regulated Adaptive Threshold (HAT) mechanism in which each neuron’s firing threshold is updated at every time step in proportion to the deviation between its exponentially smoothed firing rate and a designer-specified target rate. The rule is derived from the proportional control framework and mirrors the intrinsic excitability regulation observed in biological cortical circuits. A novel metric, the Target Achievement Error (TAE), is defined to quantify how faithfully the population reaches its intended operating point. Computational cost is assessed using a synaptic operations (SynOps) proxy that is hardware-agnostic and scales linearly with spike volume. A two-stage screening procedure selects the best configurations from 27 candidates by first enforcing an accuracy constraint and then ranking them by spike reduction, TAE, energy, and accuracy. Controlled experiments on MNIST show that the fixed-threshold baseline attains a mean validation accuracy of 92.52%±1.13% across three random seeds, with an average of 21.86 × 106 spikes and an estimated SynOps energy of 211.70 mJ. The top-ranked homeostatic configuration (α = 0.1, ftarget = 0.1, γ = 0.2) achieves 92.02% validation accuracy with a 15.54% reduction in total spike activity, incurring only a 0.50% absolute accuracy shortfall. These results indicate that homeostatic threshold regulation offers a structurally non-invasive route to improved inference energy in gradient-trained SNNs.
