ETTFS: An Efficient Training Framework for Time-to-First-Spike Neuron
Spiking Neural Networks (SNNs) have attracted considerable attention due to their biologically inspired, event-driven nature, making them highly suitable for neuromorphic hardware. Time-to-First-Spike (TTFS) coding, where neurons fire only once during inference, offers the benefits of reduced spike...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Spiking Neural Networks (SNNs) have attracted considerable attention due to
their biologically inspired, event-driven nature, making them highly suitable
for neuromorphic hardware. Time-to-First-Spike (TTFS) coding, where neurons
fire only once during inference, offers the benefits of reduced spike counts,
enhanced energy efficiency, and faster processing. However, SNNs employing TTFS
coding often suffer from diminished classification accuracy. This paper
presents an efficient training framework for TTFS that not only improves
accuracy but also accelerates the training process. Unlike most previous
approaches, we first identify two key issues limiting the performance of TTFS
neurons: information disminishing and imbalanced membrane potential
distribution. To address these challenges, we propose a novel initialization
strategy. Additionally, we introduce a temporal weighting decoding method that
aggregates temporal outputs through a weighted sum, supporting BPTT. Moreover,
we re-evaluate the pooling layer in TTFS neurons and find that average pooling
is better suited than max-pooling for this coding scheme. Our experimental
results show that the proposed training framework leads to more stable training
and significant performance improvements, achieving state-of-the-art (SOTA)
results on both the MNIST and Fashion-MNIST datasets. |
---|---|
DOI: | 10.48550/arxiv.2410.23619 |