SPIRA v2: entropy-patch tokenization + hierarchical dopamine-gated spiking cortex + hippocampal one-shot memory with replay consolidation
032a961 verified | # SPIRA β web demo (Next.js) | |
| Interactive browser demo of the SPIRA architecture. **No backend required** β the | |
| full v2 model runs client-side: | |
| - `src/lib/spira/` β TypeScript port of the Python prototype: same FNV-1a-64 / | |
| splitmix64 / mulberry32 specs, reservoir regenerated from the same seed, and the | |
| **hierarchical slow area** (windowed spike volleys, variance-matched top-down | |
| fusion with the learned gain Ξ²). Loads `public/spira_deploy.json` (~29 MB, | |
| format v2, exported by `python -m spira.export_deploy`). | |
| - `src/components/spira/` β four tabs: | |
| - **Tokenizer** β live entropy-patch segmentation with surprisal bars | |
| - **Generate** β closed-loop generation from the hierarchical spiking cortex | |
| - **One-shot memory** β teach any text in a single pass + recall with | |
| 0β3 corrupted context slots (CA3-style completion) | |
| - **Brain activity** β spike-raster playback of the recorded reservoir | |
| ## Run | |
| ```bash | |
| npm install # or: bun install | |
| npm run dev # http://localhost:3000 | |
| ``` | |
| Build for production: `npm run build && npm start`. | |
| ## Regenerating the deploy artifact | |
| ```bash | |
| cd ../python | |
| python3 -m spira.export_deploy --model artifacts/spira_model.npz \ | |
| --out ../web/public/spira_deploy.json --am-cap 100000 --am-min-count 1 | |
| ``` | |
| The spike raster (`public/spira_raster.json`) is exported from | |
| `artifacts/spira_model.npz.raster.npz` recorded during training. | |
| Hippocampal replay (consolidation) is a Python-side capability β see | |
| `../python/README.md`; the browser demo keeps the one-pass teach + recall loop. | |