| --- |
| license: other |
| license_name: other |
| license_link: LICENSE |
| --- |
| --- |
| tags: |
| - green-ai |
| - edge-computing |
| - c++ |
| - spectral-graph-theory |
| - ramanujan-graphs |
| - topological-deep-learning |
| license: other |
| --- |
|
|
| # ⚡ Ramanujan Spectral Reservoir (RSR) |
|
|
| > **"Intelligence is not about weight adjustment, but optimal topology."** |
|
|
| This repository hosts the reference implementation and benchmarks for the **Ramanujan Spectral Reservoir**, a topological AI architecture that replaces Backpropagation with closed-form solutions on spectral expander graphs. |
|
|
| ## 🚀 Key Benchmarks |
| We achieved **hard real-time** performance on commodity hardware by eliminating iterative training in hidden layers: |
|
|
| | Device | Metric | Result | Speedup vs MLP | |
| | :--- | :--- | :--- | :--- | |
| | **Legacy CPU (i5-4570, 4th Gen)** | Inference Time | **~287x Faster** | 287x | |
| | **Mobile (Android ARM64)** | Latency | **< 0.6 ms** | >100x | |
| | **Throughput** | FPS | **1600+ inf/sec** | N/A | |
|
|
| ## 📄 The Paper |
| Full mathematical derivation, proofs, and the "Poliform Industrial Secret Protocol" details are available on Zenodo: |
| **[LINK A TU ZENODO AQUÍ]** |
|
|
| ## 🔧 How it Works |
| 1. **Project:** Input data is projected onto a fixed **Ramanujan Graph** ($d$-regular spectral expander). |
| 2. **Diffuse:** Information propagates via spectral diffusion (mixing time is optimal). |
| 3. **Solve:** The readout layer is computed analytically (Closed-Form) using Ridge Regression. |
| 4. **Result:** Deterministic, Green AI that runs on bare metal C++. |
|
|
| ## 💻 Code Availability |
| The C++ kernel for Android and the Python reference implementation are available under the **Polyform Strict License 1.0.0** (Non-commercial research only). |
|
|
| --- |
| *Developed by Andrés Sebastián Pirolo (Independent Researcher).* |
| *Contact: apirolo@abc.gob.ar* |
|
|
