metadata
language: en
license: mit
library_name: pytorch
tags:
- spiking-neural-network
- neuromorphic
- surrogate-gradient
- benchmark
- catalyst
- gsc
datasets:
- google-speech-commands
metrics:
- accuracy
model-index:
- name: Catalyst GSC SNN Benchmark
results:
- task:
type: audio-classification
name: Keyword Spotting
dataset:
name: Google Speech Commands v2 (12-class)
type: google-speech-commands
metrics:
- name: Float Accuracy
type: accuracy
value: 88
- name: Quantized Accuracy (int16)
type: accuracy
value: 87.5
Catalyst GSC SNN Benchmark
Spiking Neural Network for keyword spotting on Google Speech Commands using spike-to-spike delta modulation encoding.
Model Description
- Architecture: 40 → 512 (recurrent adLIF, spike-to-spike) → 12
- Neuron model: Adaptive Leaky Integrate-and-Fire (adLIF) with spike-to-spike delta encoding
- Training: Surrogate gradient BPTT, fast-sigmoid surrogate (scale=25)
- Hardware target: Catalyst N1/N2/N3 neuromorphic processors
- Quantization: Float32 weights -> int16, membrane decay -> 12-bit fixed-point
Results
| Metric | Value |
|---|---|
| Float accuracy | 88.0% |
| Quantized accuracy (int16) | 87.5% |
| Parameters | 290,828 |
| Quantization loss | 0.5% |
Reproduce
git clone https://github.com/catalyst-neuromorphic/catalyst-benchmarks.git
cd catalyst-benchmarks
pip install -e .
python gsc/train.py --device cuda:0
Deploy to Catalyst Hardware
import catalyst_cloud
client = catalyst_cloud.Client()
result = client.simulate(
model="catalyst-neuromorphic/gsc-snn-benchmark",
input_data=your_spikes,
processor="n2"
)
Links
- Benchmark repo: catalyst-neuromorphic/catalyst-benchmarks
- Cloud API: catalyst-neuromorphic.com
- N2 paper: Zenodo DOI 10.5281/zenodo.18728256
- N1 paper: Zenodo DOI 10.5281/zenodo.18727094
Citation
@misc{catalyst-benchmarks-2026,
author = {Shulayev Barnes, Henry},
title = {Catalyst Neuromorphic Benchmarks},
year = {2026},
url = {https://github.com/catalyst-neuromorphic/catalyst-benchmarks}
}