While most machine translation systems to date are trained on large parallel corpora, humans learn language in a different way: by being grounded in an environment and interacting with other humans. In this work, we propose a communication game where two agents, native speakers of their own respective languages, jointly learn to solve a visual referential task. We find that the ability to under...

A permanent physical fault in communication lines usually leads to a failure. The feasibility of evolution of a self organized communication is studied in this paper to defeat this problem. In this case a communication protocol may emerge between blocks and also can adapt itself to environmental changes like physical faults and defects. In spite of faults, blocks may continue to function since ...

We describe four series of experiments to study the emergence of inherently meaningful communication by synthetic evolution in a population of artificial agents, which are controlled either by finite state machines or by neural networks. We found that the agents can evolve the ability to use single symbols and, to a limited extent, pairs of symbols exhibiting rudimentary syntax. We show that th...

Slime moulds are well studied organisms in biology. They are some of the simplest organisms that exhibit complex emergent behaviour. Although individual organisms interact with the environment only by following local rules, slime moulds produce a collective behaviour on a global scale. The modelling of slime mould patterns provides a good testbed for studying emergent behaviour. We have simulat...

We conducted an exploratory study to examine the unique electronic mail usage patterns exhibited by the emergent leaders in seven teams of senior executives of a federal government agency. The team members worked together over ten weeks via electronic mail in the context of an executive development program. The goal of the analysis was to identify the distinct patterns of communication behavior...