FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping

TL;DR

FiTS introduces a novel spiking neuron model that enhances temporal processing by explicitly modeling frequency selectivity and temporal shaping, leading to improved interpretability and performance on auditory tasks.

Contribution

The paper proposes FiTS, a new neuron design that factorizes temporal computation into frequency selectivity and temporal shaping, offering interpretability and improved accuracy.

Findings

FiTS outperforms plain LIF neurons on auditory benchmarks.

FiTS provides interpretable neuron-level summaries of frequency and timing.

FiTS remains competitive with strong temporal SNN baselines.

Abstract

Spiking Neural Networks (SNNs) are a promising framework for event-driven temporal processing. Prior work has improved temporal modeling through richer neuron dynamics and network-level mechanisms such as recurrence and delays, but it remains unclear how individual spiking neurons should specialize within a network. In this work, we introduce FiTS, a spiking neuron that factorizes temporal computation within each neuron into Frequency Selectivity (FS) and Temporal Shaping (TS). The FS module parameterizes each neuron's target frequency as the maximizer of its subthreshold magnitude response, while the TS module reshapes when frequency components contribute to membrane voltage accumulation through group-delay modulation. On auditory benchmarks where frequency selectivity and timing are central to the input structure, FiTS consistently improves over a plain Leaky Integrate-and-Fire (LIF) baseline in simple feedforward SNNs without recurrence or network-level delays, while remaining competitive with strong temporal SNN baselines. Beyond accuracy, the learned target frequencies and group-delay shifts provide interpretable neuron-level summaries of the frequency and timing organization learned within the network.