Toward a Cognitive System Algebra: Application to Facial Expression Learning and Imitation

In this paper, we try to demonstrate the capability of a very simple architecture to learn to recognize and reproduce facial expressions without the innate capability to recognize the facial expressions of others. In the first part, the main properties of an algebra useful to describe architectures devoted to the control of autonomous and embodied intelligent systems are described. Next, we propose a very simple architecture and study the conditions for a stable behavior learning. We show the solution relies on the importance of the interactions with another system/agent knowing already a set of emotional expressions. A condition for the learning stability of the proposed architecture is derived. The teacher agent must act as a mirror of the baby agent (and not as a classical teacher). In conclusion, we discuss the limitations of the proposed formalism and encourage people to imagine more powerful theoretical frameworks in order to compare and analyze the different intelligent systems that could be developed.

[1]  M. Asada,et al.  How does an infant acquire the ability of joint attention?: A Constructive Approach , 2003 .

[2]  E. Reed.  The Ecological Approach to Visual Perception , 1989 .

[3]  Philippe Gaussier,et al.  PerAc: A neural architecture to control artificial animals , 1995, Robotics Auton. Syst..

[4]  Gregor Schöner,et al.  Dynamics of behavior: Theory and applications for autonomous robot architectures , 1995, Robotics Auton. Syst..

[5]  J. Nadel,et al.  Toward communication: First imitations in infants, low-functioning children with autism and robots , 2004 .

[6]  K. Scherer.  Emotion as a multicomponent process: A model and some cross-cultural data. , 1984 .

[7]  Sorin Moga,et al.  From Perception-Action Loops to Imitation Processes: A Bottom-Up Approach of Learning by Imitation , 1998, Appl. Artif. Intell..

[8]  E. Robinson.  Cybernetics, or Control and Communication in the Animal and the Machine , 1963 .

[9]  P. Gaussier,et al.  Formalization of recognition, affordances and learning in isolated or interacting animats , 2022 .

[10]  Luc Steels,et al.  A case study in the behavior-oriented design of autonomous agents , 1994 .

[11]  Olaf Sporns,et al.  Classes of network connectivity and dynamics , 2001, Complex..

[12]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[13]  Tim Smithers,et al.  On quantitative performance measures of robot behaviour , 1995, Robotics Auton. Syst..

[14]  Norbert Wiener,et al.  Cybernetics, or control and communication in the animal and the machine, 2nd ed. , 1961 .

[15]  Lola Cañamero,et al.  EMOTIONS AND ADAPTATION IN AUTONOMOUS AGENTS: A DESIGN PERSPECTIVE , 2001, Cybern. Syst..

[16]  J. Decety,et al.  Neural correlates of feeling sympathy , 2003, Neuropsychologia.

[17]  Sorin Moga,et al.  Learning and communication via imitation: an autonomous robot perspective , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[18]  Kenneth L. Artis.  Design for a Brain , 1961 .

[19]  S. Feinman.  Social Referencing and the Social Construction of Reality in Infancy , 1992 .