Modelers, researchers, and developers working with generative models and wanting interoperable notation.
A text-based notation system for communicating generative models and Active Inference systems.
Lead: Daniel Friedman
Generalized Notation Notation (GNN) is a text-based notation project for communicating and specifying generative models. It provides a shared language for describing Active Inference and related models in a way that is both human-readable and machine-processable, enabling interoperability across tools and codebases.
GNN defines a notation system for generative models used in Active Inference and related frameworks. By standardizing how models are described, GNN enables clearer communication between researchers, easier translation between implementations, and more robust tooling around model specification and analysis.
GNN was originally published as Smékal and Friedman (2023) in the Active Inference Journal, archived openly on Zenodo.
GNN has an active repository and has been used across several Institute projects. Documentation and examples are available through the repository.
Contributions include specification work, tooling development, documentation, and applying GNN to new modeling domains. Background in formal modeling or Active Inference is helpful.
Related resources
Audience: Newcomer
Primary public community channel for conversation, coordination, and newcomer orientation.
Audience: Developer
Public GitHub organization for Institute repositories and open-source work.
Audience: Developer
Generalized Notation Notation project repository for model communication.
Audience: Researcher
Journal article (2023) by Smékal et al., archived on Zenodo.
Repositories
Audience: Developer
Generalized Notation Notation project for text-based model specification and communication.