Implementation of Semantic Memory in a machine conscious system based on the CONAIM architecture

• Grant number: 15/11768-2
• Support type: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): December 01, 2015
• Effective date (End): November 30, 2016
• Field of knowledge: Engineering - Electrical Engineering - Industrial Electronics, Electronic Systems and Controls
• Principal researcher: Alexandre da Silva Simões
• Grantee: Leonardo de Lellis Rossi
• Home Institution: Instituto de Ciência e Tecnologia. Universidade Estadual Paulista (UNESP). Campus de Sorocaba. Sorocaba , SP, Brazil

Abstract

Understanding consciousness is one of the most fascinating challenges of our time. From ancient civilizations to modern philosophers, questions have been asked on how one is conscious about his/her own existence and about the world that surrounds him/her. Although there is no precise definition for consciousness, there is an agreement that it is strongly related to human cognitive processes linked as a complex system. One of the key processes related to consciousness is attention, a cognitive process capable of promoting a selection of just a few stimuli among a huge number of information that reaches us constantly. In order to bring the consciousness discussion to a computational scenario, previous works presented CONAIM (Conscious Attention-based Integrated Model), a formal model for machine consciousness based on an attentional schema for human-like agent cognition that integrates: short and long term memories, reasoning, planning, emotion, decision making, learning, motivation and volition. Experimental results under a mobile robotics domain suggest that the agent can demonstrate awareness, sentience, self-awareness, self-consciousness, auto noetic consciousness, fineness, volition and perspectivalness based on exogenous and endogenous stimuli. By performing computation over an attentional space, the model also allowed the agent to learn over a 95% reduced space-state. This work proposes the development and computational implementation of the semantic memory of the CONAIM model.