Upload README.md with huggingface_hub

README.md

@@ -14,7 +14,7 @@ datasets:
 metrics:
   - accuracy
 model-index:
-  - name: Catalyst SHD SNN Benchmark
+  - name: Catalyst SHD SNN Benchmark (N3)
     results:
       - task:
           type: audio-classification
@@ -23,34 +23,28 @@ model-index:
           name: Spiking Heidelberg Digits (SHD)
           type: shd
         metrics:
-          - name: Float Accuracy
+          - name: Float Accuracy (N3)
             type: accuracy
-            value: 90.68
-          - name: Quantized Accuracy (int16)
-            type: accuracy
-            value: 90.2
+            value: 91.0
 ---
 
-# Catalyst SHD SNN Benchmark
+# Catalyst SHD SNN Benchmark (N3)
 
-Spiking Neural Network for spoken digit classification on SHD.
+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**: 700 → 1024 (recurrent adLIF) → 20
-- **Neuron model**: Adaptive Leaky Integrate-and-Fire (adLIF) with Symplectic Euler discretization
+- **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 N1/N2/N3 neuromorphic processors
-- **Quantization**: Float32 weights -> int16, membrane decay -> 12-bit fixed-point
+- **Hardware target**: Catalyst N3 neuromorphic processor
 
 ## Results
 
 | Metric | Value |
 |--------|-------|
-| Float accuracy | 90.68% |
-| Quantized accuracy (int16) | 90.2% |
-| Parameters | 1,789,972 |
-| Quantization loss | 0.5% |
+| Float accuracy | 91.0% |
+| Parameters | 3,470,484 |
 
 ## Reproduce
 
@@ -58,26 +52,14 @@ Spiking Neural Network for spoken digit classification on SHD.
 git clone https://github.com/catalyst-neuromorphic/catalyst-benchmarks.git
 cd catalyst-benchmarks
 pip install -e .
-python shd/train.py --device cuda:0
-```
-
-## Deploy to Catalyst Hardware
-
-```python
-import catalyst_cloud
-
-client = catalyst_cloud.Client()
-result = client.simulate(
-    model="catalyst-neuromorphic/shd-snn-benchmark",
-    input_data=your_spikes,
-    processor="n2"
-)
+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)