TY - GEN
T1 - Learning a common language through an emergent interaction topology
AU - Swarup, Samarth
AU - Lakkaraju, Kiran
AU - Gasser, Les
PY - 2006
Y1 - 2006
N2 - We study the effects of various emergent topologies of interaction on the rate of language convergence in a population of communicating agents. The agents generate, parse, and learn sentences from each other using recurrent neural networks. An agent chooses another agent to learn from, based on that agent's fitness. Fitness is defined to include a frequency-dependent term capturing the approximate number of interactions an agent has had with others - its "popularity" as a teacher. This method of frequency-dependent selection is based on our earlier Noisy Preferential Attachment algorithm, which has been shown to produce various network topologies, including scale-free and small-world networks. We show that convergence occurs much more quickly with this strategy than it does for uniformly random interactions. In addition, this strategy more closely represents choice preference dynamics in large natural populations, and so may be more realistic as a model for adaptive language.
AB - We study the effects of various emergent topologies of interaction on the rate of language convergence in a population of communicating agents. The agents generate, parse, and learn sentences from each other using recurrent neural networks. An agent chooses another agent to learn from, based on that agent's fitness. Fitness is defined to include a frequency-dependent term capturing the approximate number of interactions an agent has had with others - its "popularity" as a teacher. This method of frequency-dependent selection is based on our earlier Noisy Preferential Attachment algorithm, which has been shown to produce various network topologies, including scale-free and small-world networks. We show that convergence occurs much more quickly with this strategy than it does for uniformly random interactions. In addition, this strategy more closely represents choice preference dynamics in large natural populations, and so may be more realistic as a model for adaptive language.
KW - Language evolution
KW - Preferential attachment
KW - Scale free networks
UR - http://www.scopus.com/inward/record.url?scp=34247204811&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34247204811&partnerID=8YFLogxK
U2 - 10.1145/1160633.1160891
DO - 10.1145/1160633.1160891
M3 - Conference contribution
AN - SCOPUS:34247204811
SN - 1595933034
SN - 9781595933034
T3 - Proceedings of the International Conference on Autonomous Agents
SP - 1381
EP - 1383
BT - Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems
T2 - Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Y2 - 8 May 2006 through 12 May 2006
ER -