Accuracy-efficiency trade-offs in spiking neural networks: A Lempel-Ziv complexity perspective on learning rules

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) [1], we use Lempel-Ziv complexity (LZC) as a compact, analysis-oriented 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 temporal representation analysis stage. 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 generally yielded the highest observed accuracy values, although several pairwise differences were not statistically significant, while simultaneously incurring substantially higher computational cost. These results highlight that selecting a learning rule should be guided by application constraints and the desired balance between separability and computational overhead.