A mathematical theory for understanding when abstract representations emerge in neural networks.
Year: 2026
Type: preprint
Source: PubMed
Authors: Bin Wang, Jeffrey Johnston, Stefano Fusi
Institution: Columbia University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: closed
Funder: National Institutes of Health
OpenAlex ID: W7141771547