Three-Factor Delay Learning Rules for Spiking Neural Networks: Experimental Results

Luke Vassallo published a research paper on figshare in May 2026 detailing methods for spiking neural networks. The 128.6 KB PDF describes experiments on the SHD speech recognition dataset, showing performance improvements from learnable synaptic and axonal delays. The findings aim to benefit the design of power and area-constrained neuromorphic processors.

Use Cases

• Benchmarking online learning rules for SNNs based on the described three-factor delay learning method.
• Evaluating model efficiency for resource-constrained environments based on reported reductions in model size and latency.
• Studying temporal pattern recognition in SNNs based on the incorporation of learnable synaptic and axonal delays.

Strengths

• The paper reports an 18% accuracy improvement over a weights-only baseline.
• The method reduces model size by 6.6× and inference latency by 50% with a 2.5% accuracy trade-off.
• Results are benchmarked on the SHD speech recognition dataset.

Limitations

• The dataset is a 128.6 KB PDF, which is a research paper, not a primary data artifact.
• Column-level documentation for any underlying data is absent; field semantics must be inferred from the paper.
• Row count and data structure for experimental results are unknown.

Provenance

Source

Luke Vassallo via figshare.

Collection Method

Likely contains experimental results from simulations or benchmarks described in the research paper.

Time Range

null

Freshness

Last updated 2026-05-20 05:23:35.

Geography

null