NeuroTunes generates personalized, physiologically-informed therapeutic music — and gives clinicians and ML researchers the tools to study it, improve it, and build on it.
NeuroTunes™ — Patent Pending · Open source, closed weights
The same platform, three tailored entry points.
Everything below is implemented in the open-source code today.
Emotion → clinical-parameter mapping with binaural-beat encoding, bounded by an explicit parameter safety validator.
Feedback-driven reward model with held-out R² + k-fold cross-validation and champion/challenger promotion gating.
Federated coordinator with secure aggregation (HE + Shamir) and differential privacy (ε = 1.0) for multi-site training.
A basic IRB / informed-consent gate (verify_consent) records a protocol reference alongside consent-gated sessions.
Scoped, rate-limited API keys over a stable /api/v1 surface — built for machine-to-machine research use.
Open-source code, an OpenAPI spec, interactive Swagger docs, and a Python SDK. Model weights are closed.
An honest snapshot of what is built versus what is future work. We do not claim clinical-grade completeness that has not been validated.
Weekly batch retraining with a 50+ feedback threshold and t-test significance gating.
Held-out R²/MSE and 5-fold cross-validation persisted to reward_metrics.json.
A challenger is promoted only if its held-out R² ≥ champion − tolerance, else rollback.
Hard clamps + recommended-range warnings wired into both generation endpoints.
Coordinator, HE + Shamir secure aggregation, and differential privacy (ε = 1.0).
Version registry with manual/approval-gated distributed rollback and risk assessment.
Clinical efficacy scoring exists; a longitudinal per-user outcome dashboard does not yet.
The flagship open ML item: shared backbone + per-condition adapters for cross-condition learning.
Infrastructure is built; validation across ≥2 real sites is future work with partner institutions.
A privacy feature (client-side sentiment); not present today.