Self-consciousness for artificial entities using modular neural networks

  • Authors:

  • Milton Martinez Luaces;Celina Gayoso Rocha;Juan Pazos Sierra;Alfonso Rodriguez Patón

  • Affiliations:

  • Department of Artificial Intelligence, Polytechnic University of Madrid, Madrid, España;Department of Artificial Intelligence, Polytechnic University of Madrid, Madrid, España;Department of Artificial Intelligence, Polytechnic University of Madrid, Madrid, España;Department of Artificial Intelligence, Polytechnic University of Madrid, Madrid, España

  • Venue:
  • NN'08 Proceedings of the 9th WSEAS International Conference on Neural Networks
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

One of the most puzzling cognitive features is self-consciousness. A considerable amount of research has been conducted on this question in different fields like Psychology, Neurobiology and Cognitive Science. Self-consciousness implies not only self or group recognition, but also real knowledge of one's own identity. In this paper, a cognitive architecture of self-consciousness for autonomous artificial entities (holons) is proposed. This cognitive architecture includes: abstraction, self-representation, other individuals' representation, and action modules. It also includes a learning process of self-representation by direct (self-experience based) and observational learning (based on the observation of other individuals). For model implementation a new approach is taken using Modular Artificial Neural Networks (MANN) due to their biological inspiration, modularity and adaptability. We explain the cognitive architecture that enables dynamic self-representation. For model testing a multi-holon virtual environment was implemented. We analyse the effect of holon interaction, focusing on the evolution of the holon's abstract self-representation. Finally, the results are explained and analysed and conclusions drawn.