--- language: en license: mit library_name: pytorch tags: - spiking-neural-network - neuromorphic - surrogate-gradient - benchmark - catalyst - shd datasets: - shd metrics: - accuracy model-index: - name: Catalyst SHD SNN Benchmark (N3) results: - task: type: audio-classification name: Spoken Digit Classification dataset: name: Spiking Heidelberg Digits (SHD) type: shd metrics: - name: Float Accuracy (N3) type: accuracy value: 91.0 --- # Catalyst SHD SNN Benchmark (N3) Spiking Neural Network for spoken digit classification on SHD. #1 SOTA (91.0%), beating SpikFormer (90.4%) and Loihi 2 (90.9%). ## Model Description - **Architecture (N3)**: 700 → 1536 (recurrent adLIF) → 20 - **Neuron model**: Adaptive Leaky Integrate-and-Fire (adLIF) with learnable per-neuron thresholds - **Training**: Surrogate gradient BPTT, fast-sigmoid surrogate (scale=25) - **Hardware target**: Catalyst N3 neuromorphic processor ## Results | Metric | Value | |--------|-------| | Float accuracy | 91.0% | | Parameters | 3,470,484 | ## Reproduce ```bash git clone https://github.com/catalyst-neuromorphic/catalyst-benchmarks.git cd catalyst-benchmarks pip install -e . python shd/train.py --neuron adlif --hidden 1536 --epochs 200 --device cuda:0 --amp ``` ## 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} } ```