From Signals to Knowledge and from Knowledge to Action: Peircean Semiotics and the Grounding of Cognition

Abstract

Cognition is meant as the process of acquiring knowledge from the world. This process is supposed to happen within agents, which build such knowledge with the purpose to use it to determine their actions on the world. Following Peircean ideas, we postulate that such knowledge is encoded by means of signs. According to Peirce, signs are anything that can be used to represent anything else. Also, for Peirce, to represent means to be able to generate another sign, called the interpretant of the original sign, which still holds the same power of interpretability, I.e, its power to be transformed into a new sign, holding this same power. This happens through a process called semiosis, the process by which a sign is transformed into an interpretant. This whole process is performed with the aim of subsidizing the agent in deciding its behavior. So, even though the semiosis process has the power to continue infinitely, it usually stops whenever the generated interpretant brings enough information in order for the agent to effectively act in the world. We take signals to be the substract of signs. Signals are any physical property, which can be measured and captured by the agent, by means of its sensors. This includes any kind of internal memory the agent is able to have access, in order to operate. In this sense, signs can be both in the world (if these signals come from sensors) and within the own agent’s mind (if signals come from an internal memory). We understand an agent’s mind as the agents’ control system. In either case, signals can be abstracted as numbers. Not simply numbers, but numbers coming from specific sensors or specific memories. Using ideas from Peircean philosophy, in this work we postulate a pathway, in which signals, collected by either sensors or memory, can be organized in such a way that they can be effectively used as knowledge, in order for an agent to be able to decide its actions on the world, on the pursuit of its internal motivations. We postulate that agents identify and create a model of the world based on possibilities, existents, and laws, and based on this model, they are able to decide an action that maximizes the chance for the world to gain a shape, which the agents intend for it to be. This theory is postulated particularly for the case of artificial autonomous agents, meant to be constructed by engineering artifacts.