Spiking Neural Network & Neuromorphic Vision Vault (spiking-neural-network-vault)

Comprehensive scientific research vault housing algorithms, asynchronous DVS event camera simulators, Leaky Integrate-and-Fire (LIF) numerical solvers, and SynOps energy profilers for Spiking Neural Networks (SNN) and neuromorphic computing.

Vault Repository Structure

spiking-neural-network-vault/
β”œβ”€β”€ src/
β”‚   β”œβ”€β”€ dvs_event_camera.py       # Asynchronous log-intensity contrast event generator
β”‚   β”œβ”€β”€ lif_neuron_simulator.py   # Multi-neuron LIF ODE integrator with surrogate gradients
β”‚   └── synops_energy_profiler.py # SynOps vs Dense FLOPs CMOS energy accounting
β”œβ”€β”€ benchmarks/
β”‚   └── eval_neuromorphic_snn.py  # End-to-end event stream & SNN sparsity verification suite
β”œβ”€β”€ MANIFEST.json                 # Cryptographic SHA-256 integrity manifest
└── README.md                     # Biophysical equations and usage documentation

Equations

  • Log-Intensity Event Contrast: $$\Delta \ln I(x, y, t) = \ln I(x, y, t) - \ln I(x, y, t - \Delta t) \ge \pm \theta$$
  • Leaky Integrate-and-Fire Dynamics: $$\tau_m \frac{d V_i(t)}{dt} = -(V_i(t) - V_{\text{rest}}) + R I_i(t)$$
  • Surrogate Gradient (Fast Sigmoid): $$\frac{\partial S}{\partial V} \approx \frac{1}{(1 + \alpha |V - V_{\text{th}}|)^2}$$

Reproducibility

python benchmarks/eval_neuromorphic_snn.py

Developed by Ramprasad Atluri (At1uri).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support