# Accuracy-Efficiency Trade-Offs in Spiking Neural Networks: A Lempel-Ziv Complexity Perspective on Learning Rules

arXiv: https://arxiv.org/abs/2506.06750 · HTML: https://mlsanity.com/paper/2506.06750/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 7 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [Improving Stability and Performance of Spiking Neural Networks through Enhancing Temporal Consistency](https://mlsanity.com/paper/2305.14174/) (2023)
- [SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networks](https://mlsanity.com/paper/2206.09449/) (2022)
- [Low Latency Conversion of Artificial Neural Network Models to Rate-encoded Spiking Neural Networks](https://mlsanity.com/paper/2211.08410/) (2022)
- [Temporal code versus rate code for binary Information Sources](https://mlsanity.com/paper/1603.02798/) (2016)
- [Artificial Intelligence-based algorithms in medical image scan seg-mentation and intelligent visual-content generation -- a concise overview](https://mlsanity.com/paper/2401.09857/) (2024)
- [Meta-Learning in Spiking Neural Networks with Reward-Modulated STDP](https://mlsanity.com/paper/2306.04410/) (2023)
- [SAEN-BGS: Energy-Efficient Spiking AutoEncoder Network for Background Subtraction](https://mlsanity.com/paper/2505.07336/) (2025)

## Abstract (arXiv)

Training spiking neural networks (SNNs) remains challenging due to temporal dynamics, non-differentiability of spike events, and sparse event-driven activations. This paper studies how the choice of learning paradigm (unsupervised, supervised, and hybrid) affects classification performance and computational cost in temporal pattern recognition. Building on our earlier study [Rudnicka et al., 2026], we use Lempel-Ziv complexity (LZC) as a compact, decision-relevant descriptor of spike-train temporal organization to quantify how different learning rules reshape class-conditional temporal structure. The pipeline combines a leaky integrate-and-fire (LIF) SNN with an LZC-based decision rule. We evaluate learning rules on synthetic sources with controlled temporal statistics (Bernoulli, two-state Markov, and Poisson spike processes) and on two-class subsets of MNIST and N-MNIST. Across datasets, gradient-based learning achieves the highest accuracy but at high computational cost, whereas bio-inspired rules (e.g., Tempotron and SpikeProp) offer favorable accuracy--efficiency trade-offs. These results highlight that selecting a learning rule should be guided by application constraints and the desired balance between separability and computational overhead.