CIS 5590.004. Artificial General Intelligence

Concept and Learning

1. Models of Concept

• Classical view: definition, necessary and sufficient condition
• Prototype, exemplar, rule-based
• Concept hierarchy and taxonomies, basic-level concepts

• Semantic networks
• Conceptual graphs
• Knowledge graphs

• Conceptual space
• Semantic space
• Vector space

• "Grandmother cell" vs. Ensemble coding
• Compositionality, Conceptual blending
• Vector Symbolic Architecture (VSA)

2. Models of Learning

• A conceptual relation: supervised learning, end-to-end training of a universal function approximator
• A classification: unsupervised learning, clustering, associative memory

3. Set-Theoretic Inference Rules in NAL

NAL-2, NAL-3, NAL-4: copulas and compound terms from set theory

• Concept model: extension and intension, graded and dynamic, empirical and analytical
• Concept graph and its boundary
• copulas vs. conceptual relations
• Compound terms and concept composition
• Learning as reasoning, multi-strategies

Reading

• Non-Axiomatic Logic: A Model of Intelligent Reasoning, 2nd Edition, Chapters 6-8