Making Meaning: Semiotics Within Predictive Knowledge Architectures
This work addresses foundational issues in AI for researchers in predictive knowledge and semiotics, but it is incremental as it builds on existing predictive approaches without introducing new methods or data.
The paper tackles the problem of constructing ontologies using only predictions in reinforcement learning, concluding that predictions alone are insufficient but are integral to meaning-making, and suggests research into algorithmic methods for semantics based on predictions.
Within Reinforcement Learning, there is a fledgling approach to conceptualizing the environment in terms of predictions. Central to this predictive approach is the assertion that it is possible to construct ontologies in terms of predictions about sensation, behaviour, and time---to categorize the world into entities which express all aspects of the world using only predictions. This construction of ontologies is integral to predictive approaches to machine knowledge where objects are described exclusively in terms of how they are perceived. In this paper, we ground the Pericean model of semiotics in terms of Reinforcement Learning Methods, describing Peirce's Three Categories in the notation of General Value Functions. Using the Peircean model of semiotics, we demonstrate that predictions alone are insufficient to construct an ontology; however, we identify predictions as being integral to the meaning-making process. Moreover, we discuss how predictive knowledge provides a particularly stable foundation for semiosis\textemdash the process of making meaning\textemdash and suggest a possible avenue of research to design algorithmic methods which construct semantics and meaning using predictions.