Gnn

• Development of GNN as a standardized language for describing Active Inference models.
• Utilization of ASCII letters and punctuation structured in a Markdown-compliant source file.
• Presentation of GNN through examples drawn from existing Active Inference tutorials.
• Incorporation of various aspects of language including ontology, morphology, grammar, and pragmatics.

Key Findings

• GNN facilitates the communication and understanding of complex cognitive models.
• The structured representation of cognitive models reduces friction in collaboration and sharing among researchers.
• GNN demonstrates flexibility and expressiveness in modeling Active Inference.
• The approach encourages further exploration and development in the field of cognitive sciences.

Prerequisites

• Probability theory and Bayesian inference basics
• Free Energy Principle and generative models

🎯 Consulting & Tutoring

Daniel Ari Friedman, PhD is available for AI Research Consulting and Tutoring related to this skill.

Related Skills

See BIBLIOGRAPHY.md for the complete publication catalog and related papers.