THE COGNITIVE DEVELOPMENT OF MACHINE CONSCIOUSNESS IMPLEMENTATIONS

The progress in the machine consciousness research field has to be assessed in terms of the features demonstrated by the new models and implementations currently being designed. In this paper, we focus on the functional aspects of consciousness and propose the application of a revision of ConsScale — a biologically inspired scale for measuring cognitive development in artificial agents — in order to assess the cognitive capabilities of machine consciousness implementations. We argue that the progress in the implementation of consciousness in artificial agents can be assessed by looking at how key cognitive abilities associated to consciousness are integrated within artificial systems. Specifically, we characterize ConsScale as a partially ordered set and propose a particular dependency hierarchy for cognitive skills. Associated to that hierarchy a graphical representation of the cognitive profile of an artificial agent is presented as a helpful analytic tool. The proposed evaluation schema is discussed and applied to a number of significant machine consciousness models and implementations. Finally, the possibility of generating qualia and phenomenological states in machines is discussed in the context of the proposed analysis.

[1]  N. Block.  On a confusion about a function of consciousness , 1995, Behavioral and Brain Sciences.

[2]  A. Seth.  Causal connectivity of evolved neural networks during behavior. , 2005, Network.

[3]  Owen Holland,et al.  Architectures for functional imagination , 2009, Neurocomputing.

[4]  M. Lewis.  The Emergence of Consciousness and Its Role in Human Development , 2003, Annals of the New York Academy of Sciences.

[5]  Pentti O. A. Haikonen.  QUALIA AND CONSCIOUS MACHINES , 2009 .

[6]  Bernard J. Baars,et al.  CONSCIOUSNESS IS COMPUTATIONAL: THE LIDA MODEL OF GLOBAL WORKSPACE THEORY , 2009 .

[7]  Jun'ichi Takeno,et al.  Experiments and examination of mirror image cognition using a small robot , 2005, 2005 International Symposium on Computational Intelligence in Robotics and Automation.

[8]  Araceli Sanchis,et al.  Towards conscious-like behavior in computer game characters , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[9]  Pentti O. A. Haikonen.  Robot Brains: Circuits and Systems for Conscious Machines , 2007 .

[10]  Araceli Sanchis,et al.  Establishing a roadmap and metrics for conscious machines development , 2009, 2009 8th IEEE International Conference on Cognitive Informatics.

[11]  Hugo Gravato Marques.  Architectures for Embodied Imagination , 2009 .

[12]  Araceli Sanchis,et al.  Assessing and Characterizing the Cognitive Power of Machine Consciousness Implementations , 2009, AAAI Fall Symposium: Biologically Inspired Cognitive Architectures.

[13]  G. Tononi.  Consciousness as Integrated Information: a Provisional Manifesto , 2008, The Biological Bulletin.

[14]  Lee McCauley,et al.  LIDA: A Computational Model of Global Workspace Theory and Developmental Learning , 2007, AAAI Fall Symposium: AI and Consciousness.

[15]  G. Tononi.  An information integration theory of consciousness , 2004, BMC Neuroscience.

[16]  Joseph Weizenbaum,et al.  and Machine , 1977 .

[17]  A. Damasio.  The Feeling of What Happens: Body and Emotion in the Making of Consciousness , 1999 .

[18]  Araceli Sanchis,et al.  STRATEGIES FOR MEASURING MACHINE CONSCIOUSNESS , 2009 .

[19]  R. Stanley.  What Is Enumerative Combinatorics , 1986 .

[20]  Araceli Sanchis,et al.  ConsScale: A pragmatic scale for measuring the level of consciousness in artificial agents , 2010 .