World survey of artificial brains, Part II: Biologically inspired cognitive architectures

A number of leading cognitive architectures that are inspired by the human brain, at various levels of granularity, are reviewed and compared, with special attention paid to the way their internal structures and dynamics map onto neural processes. Four categories of Biologically Inspired Cognitive Architectures (BICAs) are considered, with multiple examples of each category briefly reviewed, and selected examples discussed in more depth: primarily symbolic architectures (e.g. ACT-R), emergentist architectures (e.g. DeSTIN), developmental robotics architectures (e.g. IM-CLEVER), and our central focus, hybrid architectures (e.g. LIDA, CLARION, 4D/RCS, DUAL, MicroPsi, and OpenCog). Given the state of the art in BICA, it is not yet possible to tell whether emulating the brain on the architectural level is going to be enough to allow rough emulation of brain function; and given the state of the art in neuroscience, it is not yet possible to connect BICAs with large-scale brain simulations in a thoroughgoing way. However, it is nonetheless possible to draw reasonably close function connections between various components of various BICAs and various brain regions and dynamics, and as both BICAs and brain simulations mature, these connections should become richer and may extend further into the domain of internal dynamics as well as overall behavior.

[1]  Douglas R. Hofstadter,et al.  Fluid Concepts and Creative Analogies , 1995 .

[2]  Xi Zhang,et al.  Top-down versus bottom-up learning in cognitive skill acquisition , 2004, Cognitive Systems Research.

[3]  Wlodzislaw Duch,et al.  Cognitive Architectures: Where do we go from here? , 2008, AGI.

[4]  Mark H. Lee,et al.  Staged Competence Learning in Developmental Robotics , 2007, Adapt. Behav..

[5]  Stan Franklin,et al.  LIDA and a Theory of Mind , 2008, AGI.

[6]  Bram Bakker,et al.  Hierarchical Reinforcement Learning Based on Subgoal Discovery and Subpolicy Specialization , 2003 .

[7]  Benjamin Kuipers,et al.  Autonomous Development of a Grounded Object Ontology by a Learning Robot , 2007, AAAI.

[8]  James S. Albus,et al.  Engineering of Mind: An Introduction to the Science of Intelligent Systems , 2001 .

[9]  J. Hawkins,et al.  On Intelligence , 2004 .

[10]  Juyang Weng,et al.  Developmental Humanoids: Humanoids that Develop Skills Automatically , 2000 .

[11]  Ben Goertzel,et al.  Using Dependency Parsing and Probabilistic Inference to Extract Relationships between Genes, Proteins and Malignancies Implicit Among Multiple Biomedical Research Abstracts , 2006, BioNLP@NAACL-HLT.

[12]  Nils J. Nilsson,et al.  The Physical Symbol System Hypothesis: Status and Prospects , 2006, 50 Years of Artificial Intelligence.

[13]  Pat Langley,et al.  An Adaptive Architecture for Physical Agents , 2005, Web Intelligence.

[14]  Jonathan D. Cohen,et al.  A Biologically Based Computational Model of Working Memory , 1999 .

[15]  Giulio Sandini,et al.  The iCub humanoid robot: an open platform for research in embodied cognition , 2008, PerMIS.

[16]  Max Lungarella,et al.  Developmental Robotics , 2009, Encyclopedia of Artificial Intelligence.

[17]  Ben Goertzel,et al.  Probabilistic Logic Networks , 2009 .

[18]  Paul Sambre,et al.  Gilles Fauconnier & Mark Turner, " The way we think: conceptual blending and the mind's hidden complexities" , 2002 .

[19]  Jürgen Schmidhuber,et al.  Optimal Artificial Curiosity, Creativity, Music, and the Fine Arts , 2005 .

[20]  G. Reeke.  Marvin Minsky, The Society of Mind , 1991, Artif. Intell..

[21]  Andrew G. Barto,et al.  An intrinsic reward mechanism for efficient exploration , 2006, ICML.

[22]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[23]  Stuart C. Shapiro,et al.  Metacognition in SNePS , 2007, AI Mag..

[24]  Jürgen Schmidhuber,et al.  A possibility for implementing curiosity and boredom in model-building neural controllers , 1991 .

[25]  Marvin Minsky,et al.  Em-one: an architecture for reflective commonsense thinking , 2005 .

[26]  Juyang Weng,et al.  From neural networks to the brain: autonomous mental development , 2006, IEEE Computational Intelligence Magazine.

[27]  Pierre-Yves Oudeyer,et al.  Discovering communication , 2006, Connect. Sci..

[28]  Jürgen Schmidhuber,et al.  Exploring the predictable , 2003 .

[29]  Jürgen Schmidhuber,et al.  Quasi-online reinforcement learning for robots , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[30]  L. Shastri,et al.  From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony , 1993, Behavioral and Brain Sciences.

[31]  Jürgen Schmidhuber,et al.  Curious model-building control systems , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[32]  James S. Albus,et al.  Reverse Engineering the Brain , 2010, AAAI Fall Symposium: Biologically Inspired Cognitive Architectures.

[33]  D E Kieras,et al.  A computational theory of executive cognitive processes and multiple-task performance: Part 1. Basic mechanisms. , 1997, Psychological review.

[34]  Nicholas L. Cassimatis.  Adaptive Algorithmic Hybrids for Human-Level Artificial Intelligence , 2006, AGI.

[35]  F. Craik,et al.  The Oxford handbook of memory , 2006 .

[36]  Frederic Kaplan.  Neurorobotics: An Experimental Science of Embodiment , 2008, Front. Neurosci..

[37]  John R. Anderson,et al.  A central circuit of the mind , 2008, Trends in Cognitive Sciences.

[38]  B. Kokinov,et al.  TOWARDS ACTIVE VISION IN THE DUAL COGNITIVE ARCHITECTURE , 2006 .

[39]  Saint Louis,et al.  Competent Program Evolution , 2006 .

[40]  Benjamin Kuipers,et al.  Towards the Application of Reinforcement Learning to Undirected Developmental Learning , 2007 .

[41]  Martin Pelikan,et al.  Hierarchical Bayesian optimization algorithm: toward a new generation of evolutionary algorithms , 2010, SICE 2003 Annual Conference (IEEE Cat. No.03TH8734).

[42]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[43]  Juyang Weng,et al.  Dav: a humanoid robot platform for autonomous mental development , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[44]  James S. Albus,et al.  RCS: A cognitive architecture for intelligent multi-agent systems , 2005, Annu. Rev. Control..

[45]  Christopher W. Myers,et al.  Meeting Newell's other challenge: Cognitive architectures as the basis for cognitive engineering , 2003, Behavioral and Brain Sciences.

[46]  Ben Goertzel,et al.  An Integrative Methodology for Teaching Embodied Non-Linguistic Agents, Applied to Virtual Animals in Second Life , 2008, AGI.

[47]  G. Edelman,et al.  Retrospective and prospective responses arising in a modeled hippocampus during maze navigation by a brain-based device , 2007, Proceedings of the National Academy of Sciences.

[48]  James S. Albus,et al.  RCS: A cognitive architecture for intelligent multi-agent systems☆ , 2004 .

[49]  Mark H. Lee,et al.  Developmental learning for autonomous robots , 2007, Robotics Auton. Syst..

[50]  Itamar Arel,et al.  DeSTIN: A Scalable Deep Learning Architecture with Application to High-Dimensional Robust Pattern Recognition , 2009, AAAI Fall Symposium: Biologically Inspired Cognitive Architectures.

[51]  M. Minsky.  The Society of Mind , 1986 .

[52]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[53]  S. Hochreiter,et al.  REINFORCEMENT DRIVEN INFORMATION ACQUISITION IN NONDETERMINISTIC ENVIRONMENTS , 1995 .

[54]  Pierre-Yves Oudeyer,et al.  R-IAC : Robust Intrinsically Motivated Active Learning , 2009 .

[55]  Ben Goertzel,et al.  XIA-MAN: An Extensible, Integrative Architecture for Intelligent Humanoid Robotics , 2008, AAAI Fall Symposium: Biologically Inspired Cognitive Architectures.

[56]  C. Lebiere,et al.  The Newell Test for a theory of cognition , 2003, Behavioral and Brain Sciences.

[57]  Nuttapong Chentanez,et al.  Intrinsically Motivated Reinforcement Learning , 2004, NIPS.

[58]  Stan Franklin,et al.  THE LIDA ARCHITECTURE: ADDING NEW MODES OF LEARNING TO AN INTELLIGENT, AUTONOMOUS, SOFTWARE AGENT , 2006 .