Computational Autonomous Mental Development: A White Paper for Suggesting a New Initiative

Abstract : A new synthesis of the neural, behavioral, and computer sciences is on the horizon. The topic that promises to unite these disparate fields is computational autonomous mental development. The term "mental" refers to cognitive, behavioral and other mental skills that are exhibited by humans, higher animals and artificial systems. Computational autonomous mental development refers to the computational process by which a brain-like machine, natural or artificial, develops mental skills under the guidance of an intrinsic developmental program and through its own autonomous activities using its sensors and effectors to interact with its environment. The developmental program for an animal resides in the genes as a result of many generations of evolution; while that for a machine is initially programmed into the machine by humans but the environment changes the ways that the developmental program operates. The synthesis is inspired by new discoveries in neuroscience that highlight the exquisite plasticity of the brain with experience through infancy and adulthood, by new theories and computational modeling of human cognitive development, and by methodological and computational advances in AI and robotics that make it possible for machines to autonomously develop their own intelligence. Potentially, there are enormous benefits as a result of this synthesis: For behavioral and neural scientists, it promises a deeper, more precise and more systematic understanding about the ways our brain works through the computational study of its developmental processes. For the engineering and computer sciences, there is the vision of greatly enhanced capability for machines to interact with humans and to process information to a degree that requires kinds of machine intelligence other than those possible before.

[1]  Roderic A. Grupen,et al.  A feedback control structure for on-line learning tasks , 1997, Robotics Auton. Syst..

[2]  John Juyang Weng,et al.  The Living Machine Initiative , 1996 .

[3]  M. Sur,et al.  Visual behaviour mediated by retinal projections directed to the auditory pathway , 2000, Nature.

[4]  M. Raijmakers.  Rethinking innateness: A connectionist perspective on development. , 1997 .

[5]  Juyang Weng,et al.  Toward automation of learning: the state self-organization problem for a face recognizer , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[6]  Juyang Weng,et al.  Developmental Robots: Theory, Method and Experimental Results , 1999 .

[7]  Alex Pentland,et al.  Learning audio-visual associations using mutual information , 1999, Proceedings Integration of Speech and Image Understanding.

[8]  H. Gardner.  Multiple intelligences : the theory in practice , 1993 .

[9]  T. Kuhn,et al.  The Structure of Scientific Revolutions , 1963 .

[10]  G ARTHUR,et al.  The Arthur adaptation of the Leiter international performance scale. , 1949, Journal of clinical psychology.

[11]  E. Thelen,et al.  The dynamics of embodiment: A field theory of infant perseverative reaching , 2001, Behavioral and Brain Sciences.

[12]  Xiaoqin Wang,et al.  Remodelling of hand representation in adult cortex determined by timing of tactile stimulation , 1995, Nature.

[13]  N. Bayley.  Bayley Scales of Infant Development , 1999 .

[14]  G. Edelman,et al.  Behavioral constraints in the development of neuronal properties: a cortical model embedded in a real-world device. , 1998, Cerebral cortex.