README.md

---
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

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

## Links

- **Benchmark repo**: [catalyst-neuromorphic/catalyst-benchmarks](https://github.com/catalyst-neuromorphic/catalyst-benchmarks)
- **Cloud API**: [catalyst-neuromorphic.com](https://catalyst-neuromorphic.com)
- **N3 paper**: [Zenodo DOI 10.5281/zenodo.18881283](https://zenodo.org/records/18881283)
- **N2 paper**: [Zenodo DOI 10.5281/zenodo.18728256](https://zenodo.org/records/18728256)
- **N1 paper**: [Zenodo DOI 10.5281/zenodo.18727094](https://zenodo.org/records/18727094)

## Citation

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