Vector-Symbolic Model for Socio-Cultural Tasks in ACT-R
A recent study published on arXiv (ID: 2608.02807) introduces a declarative memory framework for the ACT-R cognitive architecture, utilizing a vector-symbolic autoencoder to depict semantic connections across various levels. This model aims to enhance the understanding of how sociocultural factors influence decision-making processes. It differentiates episodic memories from semantic memory vectors derived from text through a straightforward Holographic Reduced Representation (HRR) operation, generating a final chunk activation for memory retrieval. The method tackles the issue of identifying the most relevant levels of semantic representation in specific contexts and considers self-representations in memory to explore how cultural links affect decisions. The unnamed authors presented this research as a cross-type submission, contributing to computational cognitive modeling and AI, with implications for systems that integrate cultural context. The paper can be accessed on arXiv, a repository for scientific preprints.
Key facts
- The paper is titled 'Learning a Vector-Symbolic Model for Socio-Cultural Tasks'.
- It is published on arXiv with ID 2608.02807v1.
- The research proposes a declarative memory system for the ACT-R cognitive architecture.
- The system uses a vector-symbolic autoencoder to represent semantic associations at multiple levels.
- It employs a simple HRR operation to encode episodic memories differently from semantic memory vectors.
- The goal is to better represent the impact of sociocultural structures on decision making in computational cognitive models.
- The approach accounts for self-representations in memory to determine how cultural associations shape decision making.
- The paper was announced as a cross-type submission on arXiv.
Entities
Institutions
- arXiv