A model of symbiomemesis: machine education and communication as pillars for human-autonomy symbiosis

Abstract

Symbiosis is a physiological phenomenon where organisms of different species develop social interdependencies through partnerships. Artificial agents need mechanisms to build their capacity to develop symbiotic relationships. In this paper, we discuss two pillars for these mechanisms: machine education (ME) and bi-directional communication. ME is a new revolution in artificial intelligence (AI) which aims at structuring the learning journey of AI-enabled autonomous systems. In addition to the design of a systematic curriculum, ME embeds the body of knowledge necessary for the social integration of AI, such as ethics, moral values and trust, into the evolutionary design and learning of the AI. ME promises to equip AI with skills to be ready to develop logic-based symbiosis with humans and in a manner that leads to a trustworthy and effective steady-state through the mental interaction between humans and autonomy; a state we name symbiomemesis to differentiate it from ecological symbiosis. The second pillar, bi-directional communication as a discourse enables information to flow between the AI systems and humans. We combine machine education and communication theory as the two prerequisites for symbiosis of AI agents and present a formal computational model of symbiomemesis to enable symbiotic human-autonomy teaming. This article is part of the theme issue ‘Towards symbiotic autonomous systems’.

Quo vadis artificial intelligence?

“…Training with positive examples, commonly understood as teaching and practicing, is a means for learning in the narrow sense. Beyond it, ability migration (transfer learning), critical thinking (adversarial training), imitation (imitation learning), and creativity (heuristic design) have begun to be proven as alternative effective technical routes for AI design [80,81].…”

Fusing Interpretable Knowledge of Neural Network Learning Agents For Swarm-Guidance

“…Knowledge interpretation is a process that maps the knowledge of an agent from one representation language to another [20]. Consider a system of two agents performing knowledge sharing: sender agent π and receiver agent β with knowledge representations K π and K β respectively.…”

JSwarm: A Jingulu-Inspired Human-AI-Teaming Language for Context-Aware Swarm Guidance

“…Abbass et al [34]. presented a formal definition of transparency towards bi-directional communication in human-swarm teaming systems.…”

“…The mapping from internal knowledge representation K β to a sentence S β is achieved by a transformation function R. The reverse is achieved by R −1 . Below is the set of definitions quoted from [34]. Definition 4.1 (Interpretability).…”