ssc-snn-benchmark / README.md
mrwabbit's picture
Upload README.md with huggingface_hub
9310349 verified
metadata
language: en
license: mit
library_name: pytorch
tags:
  - spiking-neural-network
  - neuromorphic
  - surrogate-gradient
  - benchmark
  - catalyst
  - ssc
datasets:
  - ssc
metrics:
  - accuracy
model-index:
  - name: Catalyst SSC SNN Benchmark (N3)
    results:
      - task:
          type: audio-classification
          name: Spoken Command Classification
        dataset:
          name: Spiking Speech Commands (SSC)
          type: ssc
        metrics:
          - name: Float Accuracy (N3)
            type: accuracy
            value: 76.4

Catalyst SSC SNN Benchmark (N3)

Spiking Neural Network for spoken command classification on SSC. Achieves 76.4% with adaptive LIF neurons.

Model Description

  • Architecture (N3): 700 → 1024 (recurrent adLIF) → 512 (adLIF) → 35
  • Neuron model: Adaptive Leaky Integrate-and-Fire (adLIF) with Symplectic Euler discretization
  • Training: Surrogate gradient BPTT, fast-sigmoid surrogate (scale=25)
  • Hardware target: Catalyst N3 neuromorphic processor

Results

Metric Value
Float accuracy 76.4%
Parameters 2,313,763

Reproduce

git clone https://github.com/catalyst-neuromorphic/catalyst-benchmarks.git
cd catalyst-benchmarks
pip install -e .
python ssc/train.py --device cuda:0

Links

Citation

@misc{catalyst-benchmarks-2026,
  author = {Shulayev Barnes, Henry},
  title = {Catalyst Neuromorphic Benchmarks},
  year = {2026},
  url = {https://github.com/catalyst-neuromorphic/catalyst-benchmarks}
}