Neuromorphic Sequential Arena: A Benchmark for Neuromorphic Temporal Processing

TL;DR

This paper addresses the lack of standardized benchmarks for neuromorphic temporal processing by proposing the Neuromorphic Sequential Arena (NSA), a seven-task, real-world temporal benchmark that encompasses diverse modalities. It integrates Segregated Temporal Probe (STP) to quantify a task's reliance on temporal dependencies and to validate the benchmark's effectiveness. Through comprehensive comparisons of multiple spiking neuron models and neural architectures, NSA reveals task- and model-specific strengths and trade-offs in accuracy, training speed, memory usage, and energy efficiency, underscoring the need for energy-conscious, temporally capable SNN designs. The NSA framework provides a reproducible, evolving platform to track progress in neuromorphic temporal processing and to guide the development of practical, low-power neuromorphic systems for real-world applications.

Abstract

Temporal processing is vital for extracting meaningful information from time-varying signals. Recent advancements in Spiking Neural Networks (SNNs) have shown immense promise in efficiently processing these signals. However, progress in this field has been impeded by the lack of effective and standardized benchmarks, which complicates the consistent measurement of technological advancements and limits the practical applicability of SNNs. To bridge this gap, we introduce the Neuromorphic Sequential Arena (NSA), a comprehensive benchmark that offers an effective, versatile, and application-oriented evaluation framework for neuromorphic temporal processing. The NSA includes seven real-world temporal processing tasks from a diverse range of application scenarios, each capturing rich temporal dynamics across multiple timescales. Utilizing NSA, we conduct extensive comparisons of recently introduced spiking neuron models and neural architectures, presenting comprehensive baselines in terms of task performance, training speed, memory usage, and energy efficiency. Our findings emphasize an urgent need for efficient SNN designs that can consistently deliver high performance across tasks with varying temporal complexities while maintaining low computational costs. NSA enables systematic tracking of advancements in neuromorphic algorithm research and paves the way for developing effective and efficient neuromorphic temporal processing systems.

Figures (1)

• Figure 1: Comparison of the three training algorithms in STP.