Simulating Language Learning in Community of Agents Using Self-Organizing Maps

Abstract

In this article, we present a model of a cognitive system, or an agent, with the following properties: it can perceive its environment, it can move in its environment, it can perform some simple actions, and it can send and receive messages. The main components of its internal structure include a working memory, a semantic memory, and a decision making mechanism. In our implemented simulation model, the agent associates linguistic expressions and visual perceptions. The main motivation for communication is to exchange information. The linguistic expressions are not symbolic but pattern-like. With the current framework and simulation tool, we wish to provide a useful model for language emergence based on the unsupervised learning paradigm among a community of communicating autonomous agents. In the future, we plan to include other aspects of cognitive modeling including more realistic multimodal information processing, anticipatory decision making, language evolution, and emotional modeling. 1 1

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 12 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.