Implementation of semantic memory in a machine conscious system based on the CONAIM architecture

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

Abstract

Understanding consciousness is one of the mostfascinating challenges of our time. From ancient civilizations tomodern philosophers, questions have been asked on how one isconscious about his/her own existence and about the world thatsurrounds him/her. Although there is no precise definition forconsciousness, there is an agreement that it is strongly related tohuman cognitive processes linked as a complex system. One ofthe key processes related to consciousness is attention, a cognitiveprocess capable of promoting a selection of just a few stimuliamong a huge number of information that reaches us constantly.In order to bring the consciousness discussion to a computationalscenario, previous works presented CONAIM (Conscious Attention-based Integrated Model), a formal model for machine consciousnessbased on an attentional schema for human-like agent cognitionthat integrates: short and long term memories, reasoning, planning,emotion, decision making, learning, motivation and volition.Experimental results under a mobile robotics domain suggest thatthe agent can demonstrate awareness, sentience, self-awareness,self-consciousness, autonoetic consciousness, mineness, volitionand perspectivalness based on exogenous and endogenous stimuli.By performing computation over an attentional space, the modelalso 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.