Social Learning in Neural Agent-Based Models

Bibliographic Data

ID10708200
AuthorsIgor Douven (0000-0003-3413-080X, Institut d'Histoire et de Philosophie des Sciences et des Techniques, corresponding author)
Year2025
Volume92
Issue1
Pages141-161
Publication date2025-01-01
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenuePhilosophy of Science (JOURNAL)
Journal identifiersISSN: 0031-8248 • E-ISSN: 1539-767X
PublisherCambridge University Press (CUP) (PUBLISHER)
DOI10.1017/psa.2024.33
OpenAlexW4403849860
LanguageEN
Citations received5
References cited58

Agent-based models (ABMs) are widely used to study how individual interactions shape collective behaviors. Critics argue that ABMs are often too simplistic to capture real-world complexities. We address this by integrating artificial neural networks into ABMs, focusing on enhancing the Hegselmann–Krause (HK) model. By using multilayer perceptrons as agents, we create more realistic ABMs that better reflect actual agents. This approach yields multiple models, as core elements of the HK model can be defined in various ways. We conduct two computational studies to compare these models with each other and with traditional individual-learning paradigms

Agent-based model · Artificial neural network · Cognitive science · Core (optical fiber) · Knowledge management · Machine learning · Perceptron · Social learning · Artificial Intelligence · Complex Network Analysis Techniques · Computer Science · Evolutionary Game Theory and Cooperation · Opinion Dynamics and Social Influence · Psychology

Tools

Open DOIOpen Access