SOURCE-LINKED INTELLIGENCE

The Emergent Symbolic Structure of Artificial Neural Networks

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Modern systems in artificial intelligence (AI) somehow excel in domains for which they seem poorly suited. Intelligence has traditionally been modeled as operating over structured combinations of symbols, such as logical formulas. However, the strongest modern AI systems are based on neural networks, which instead represent information in continuous vectors. Vectors seem inadequate for capturing the structure of language, logic, and other cognitive domains, yet neural networks achieve impressive performance in these areas. How do they do it? In this work, we propose a potential answer: Despite

Read original source ↗ Open in workspace

recordType

paper

region

Global