Downloads · 30 days
0
spike-pocket
ARotting/spike-pocket
spike-pocket is a machine learning model from ARotting. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Spike Pocket trains a leaky-integrate-and-fire neural classifier with straight-through surrogate gradients and Poisson rate coding. A conventional dense network with exactly the same weights and biases is the matched…
Access
Public
Updated Jul 30, 2026
Repo size
39.1 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors39.1 KB · 70%
At a glance
- Access
- Public
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026
- SHA
- eb9fb7bf
Model card
From the Hugging Face model README
Spike Pocket
Spike Pocket trains a leaky-integrate-and-fire neural classifier with straight-through surrogate gradients and Poisson rate coding. A conventional dense network with exactly the same weights and biases is the matched control.
Evaluation includes clean accuracy, Gaussian-noise accuracy, hidden spike rate, and a synaptic-activity proxy. Spike activity is not presented as measured hardware power; actual energy depends on a neuromorphic deployment target.
Verified local result
Both models contain exactly 4,810 parameters. The LIF network reached 98.15% clean accuracy versus 97.41% for the dense control; both reached 90.74% under Gaussian noise at standard deviation 0.20. Hidden neurons fired on 41.40% of evaluated timestep opportunities.
uv run python projects/spike-pocket/train.py
uv run pytest tests/test_spike_pocket.py
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026