Summary
An important cognitive feature-shared only by humans and a few other species- is self-consciousness. It has been defined as "the possession of the concept of the self and the ability to use this concept in thinking about oneself". Self-consciousness undoubtedly depends on some kind of self-representation, although the nature of this self-representation in intelligent beings is still unknown. In recent years, several cognitive scientists have proposed self-represent at ion models. Nevertheless, usually these models only represent the current state of consciousness. In this paper, we introduce the time dimension to extend self-representation models in order to represent the development of individual self-representation over time. Another important cognitive feature of both humans and animals is that they have a sense of belonging. It has been defined as "the process by which an individual understands that other beings are like himself (herself)". We focus on the social side of self-consciousness and self-representation by defining self-consciousness as a specialization of the sense of belonging. In this paper, we use modular artificial neural networks for implementation. To test models, we implemented a simulator with modular neural networks composed of self-organized maps (SOM) and time delayed neural networks (TDNN). In this multi-agent system, agents were equipped with a simplified model of sensory perception, personality, sense of belonging and self-consciousness. Agent interaction is tested in different hypothetical social scenarios. The simulator structure and its MANN components are described in detail. The relation between a sense of belonging and self-consciousness is also discussed. Quantitative results are analyzed and conclusions stated.
See the full content of this document
Extract
The Social Side and Time Dimension of Self-Representation in Agents Using Modular Neural Networks
1. Introduction
The nature of consciousness has been an object of considerable research in recent years. Because of its complexity, understanding consciousness was defined as "the ultimate intellectual challenge of this new millennium" (Dehaene & Changeux, 2003). Even though a complete description of consciousness is still an open problem, our knowledge in this area has been significantly improved thanks to contributions by researchers from various fields of study, mainly psychology, neuroscience and artificial intelligence. As a result, there is increasing evidence -especially from neuroscience- that consciousness is not an atomic entity. Contrariwise, it can be viewed as an integrated system with many cognitive properties. This paper focuses on some of these properties of consciousness, especially on the sense of belonging, self-consciousness and self-representa ion.A sense of belonging can be defined as the ability to identify oneself as similar to other members of one's species. An animal shows a sense of belonging when it sees itself as being "part of a particular group, and separate from other groups of the same species" (Vergio, 1999). Another cognitive ? roper ty, called self- cons ci o usn ess, means that not only does the individual have a self-concept but that they can use it for decision support (Menant, 2005). While both humans and animals share a sense of belonging to their species, self-consciousness has only been observed in humans and a few other species to date (Raiss & Marino, 2001) (Vergio, 1997).Self-consciousness is unfeasible without some sort of self-representation, and the definition of a complete model of self-representation is still an open issue. Because of its complexity, it would be rather difficult, if at all feasible, to design a complete model of self-representation for agents with the current state of the art. Through abstraction, we focus on...See the full content of this document
Sponsored links
