Cadence

Website · Paper · PyPI · Documentation

Research toward general intelligence through overlap consensus, equilibrium detuning and self-reflection.

Cadence's goal is a continuing learning system with the flexibility of animal and human problem solving: acquiring skills from experience, retaining useful knowledge, imagining alternatives and creating solutions across domains. The mission is to find the smallest persistent state and local update rule that can support these abilities. General intelligence is the research goal; the current library establishes bounded learning, memory and control results.

The organizing idea comes from Observer Patch Holography: bounded, observer-like patches with local state, ports, records, readback and repair. A disturbance exposes disagreement. The network can explore a possible response, test it against actual consequences and settle into a revised organization. We seek fewer mechanisms that solve more problems.

Three shared principles

• Overlap consensus: patches repair disagreement across their shared boundaries. The resulting equilibrium is an internally consistent model; its predictions still have to agree with experience.
• Equilibrium detuning: observed outcomes perturb that equilibrium. Local positive/negative contrasts change learned relationships; the same operation can adjust proposed actions while holding the model fixed.
• Functional self-reflection: patches can read internal state, predictions, proposed actions and unresolved mismatches through ordinary ports. Learning which internal summaries to read, how to feed them back and how to grow useful recursive organization is a central research direction.

The current implementation provides detached self-readback and private proposal revision. Automatically learned recursive hierarchies, curiosity and reliable creativity remain to be demonstrated. Creativity and self-reflection defines these goals and their behavioral tests.

Current library

Version 0.11.0 brings learning and continuous action planning into the same temporal model. It requires Python 3.11+ and NumPy:

python -m pip install cadence-net==0.11.0

Start with the executable learn, act and observe guide. It acquires an action/consequence relation, plans privately, executes bounded actions and uses actual readback to repair its next proposal. The architecture guide maps each capability to its API and current scope.

Imagined continuations are isolated. Branches use the learned network without changing live activity, parameters or factual bookkeeping. Controlled experiments demonstrate useful planning. Creativity requires additional evidence that novel proposals satisfy meaningful constraints and survive actual evaluation; musical improvisation is one possible example.

Retained experience and new learning are tested together. Protected-path memory is conditional and finite. Importance is currently supplied; automatic relevance, selective forgetting, specialization and broad skill transfer remain research requirements. The task-design guide and common missteps explain how to measure them.

General mechanisms, different applications

Games, language, multimodal perception, embodied control and creative work should use the same learning and memory mechanisms with declared observation and action ports. NES play, Connect Four, Maestro and music generation are application tests, not definitions of the architecture. A result in one does not establish transfer to the others.

Application demonstrations are published only when they establish their claimed behavior. Recall and interpolation are useful development tests; original creation requires stronger evidence. Research receipts remain available with the paper without presenting those tests as finished products.

Proofs and compatibility

The bundled Lean library contains 169 checked conditional theorems about the mathematical components and their limits. It does not certify the complete Python implementation or prove intelligence. The paper identifies assumptions and reproducible evidence.

The existing PatchNet graph interface, Brain, Learner, GenericBrain, Records and circuit APIs remain supported for existing applications. Their optional memories and construction helpers are distinct compositions, not required parts of the temporal core. API reference.

Development installs use python -m pip install -e .. Optional backends apply to their documented graph APIs; the temporal implementation is NumPy. Pin a release or exact commit for reproducible work. MIT licensed.