Sparse Gradient Training in Spiking Neural Networks: Accuracy and Latency on Tabular Data Benchmarks

The brain-inspired Spiking neural networks (SNN) claim to present advantages for visual classification tasks in terms of energy efficiency and inherent robustness. In this work, we explore the impact on network inter-layer sparsity through neural coding schemes and the intrinsic structural parameters of Leaky Integrate-and-Fire (LIF) neurons, which can be a candidate metric for performance evaluation. Towards this, we perform a comparative study of four critical neural coding schemes: rate coding (poisson coding), latency coding, phase coding, and direct coding, as well as 6 LIF neuron intrins

Research goal: How does the integration of sparse gradient training in Spiking Neural Networks compare to standard surrogate gradient methods in terms of accuracy and inference latency on tabular data benchmarks like MLP-1M or OpenML?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 9.0/10.