A Foundational Architecture for Artificial General Intelligence

Implementing and fleshing out a number of psychological and neuroscience theories of cognition, the LIDA conceptual model aims at being a cognitive “theory of everything.” With modules or processes for perception, working memory, episodic memories, “consciousness,” procedural memory, action selection, perceptual learning, episodic learning, deliberation, volition, and non-routine problem solving, the LIDA model is ideally suited to provide a working ontology that would allow for the discussion, design, and comparison of AGI systems. The LIDA architecture is based on the LIDA cognitive cycle, a sort of “cognitive atom.” The more elementary cognitive modules and processes play a role in each cognitive cycle. Higher-level processes are performed over multiple cycles. In addition to giving a quick overview of the LIDA conceptual model, and its underlying computational technology, we argue for the LIDA architecture's role as a foundational architecture for an AGI. Finally, lessons For AGI researchers drawn from the model and its architecture are discussed.

[1]  Alan K. Mackworth.  Constraint Satisfaction , 1985 .

[2]  Marco C. Bettoni,et al.  Made-Up Minds: A Constructivist Approach to Artificial Intelligence , 1993, IEEE Expert.

[3]  Stan Franklin,et al.  An action selection mechanism for "conscious" software agents , 2002 .

[4]  Lee McCauley,et al.  IDA: a cognitive agent architecture , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[5]  T. Kellam,et al.  Artificial Minds , 1996, Inf. Process. Manag..

[6]  A. Glenberg,et al.  What memory is for: Creating meaning in the service of action , 1997, Behavioral and Brain Sciences.

[7]  A. Baddeley.  The episodic buffer: a new component of working memory? , 2000, Trends in Cognitive Sciences.

[8]  M. Conway.  Sensory-perceptual episodic memory and its context: autobiographical memory. , 2001, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[9]  E Halgren,et al.  Rapid distributed fronto-parieto-occipital processing stages during working memory in humans. , 2002, Cerebral cortex.

[10]  D Lehmann,et al.  EEG alpha map series: brain micro-states by space-oriented adaptive segmentation. , 1987, Electroencephalography and clinical neurophysiology.

[11]  Stan Franklin,et al.  IDA, a Conscious Artifact? , 2006 .

[12]  Alan Baddeley,et al.  Consciousness and working memory , 1992, Consciousness and Cognition.

[13]  Juyang Weng,et al.  Developmental Robotics: Theory and Experiments , 2004, Int. J. Humanoid Robotics.

[14]  Humberto R. Maturana,et al.  The Organization of the Living , 1999 .

[15]  Arthur C. Graesser,et al.  Is it an Agent, or Just a Program?: A Taxonomy for Autonomous Agents , 1996, ATAL.

[16]  Sidney K. D'Mello,et al.  Encoding and Retrieval Efficiency of Episodic Data in a Modified Sparse Distributed Memory System , 2005 .

[17]  Sidney K. D'Mello,et al.  Modified sparse distributed memory as transient episodic memory for cognitive software agents , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[18]  Melanie Mitchell,et al.  The Copycat project: a model of mental fluidity and analogy-making , 1995 .

[19]  John V. Jackson.  Idea for a mind , 1987, SGAR.

[20]  Roman V. Belavkin.  Modelling the Inverted-U Effect with Act-r , 2002 .

[21]  S. Gallagher.  Philosophical conceptions of the self: implications for cognitive science , 2000, Trends in Cognitive Sciences.

[22]  M. Posner.  Cumulative Development of Attentional Theory. , 1982 .

[23]  Samuel T. Waters,et al.  American Association for Artificial Intelligence (AAAI) , 1988 .

[24]  W. Freeman,et al.  Aperiodic phase re‐setting in scalp EEG of beta–gamma oscillations by state transitions at alpha–theta rates , 2003, Human brain mapping.

[25]  B. Baars.  A cognitive theory of consciousness , 1988 .

[26]  Arthur Charles Clarke,et al.  Profiles of the Future : An Inquiry into the Limits of the Possible , 1999 .

[27]  William McCune,et al.  Solution of the Robbins Problem , 1997, Journal of Automated Reasoning.

[28]  Stan Franklin,et al.  Motivations, Values and Emotions: 3 sides of the same coin , 2006 .

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

[30]  B. Baars,et al.  Brain, conscious experience and the observing self , 2003, Trends in Neurosciences.

[31]  Arpad Kelemen,et al.  Constraint Satisfaction In "Conscious" Software Agents--A Practical Application , 2005, Appl. Artif. Intell..

[32]  H. Maturana,et al.  Autopoiesis and Cognition : The Realization of the Living (Boston Studies in the Philosophy of Scie , 1980 .

[33]  B. Baars,et al.  The Role of Consciousness in Memory , 2005 .

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

[35]  G. Strawson.  The self and the SESMET , 1999 .

[36]  Bernard J. Baars,et al.  A Cognitive Science Based Machine Learning Architecture , 2006, AAAI Spring Symposium: Between a Rock and a Hard Place: Cognitive Science Principles Meet AI-Hard Problems.

[37]  L. Barsalou,et al.  Whither structured representation? , 1999, Behavioral and Brain Sciences.

[38]  Stan Franklin,et al.  Deliberation and Voluntary Action in "Conscious" Software Agents , 2000 .

[39]  T. Koenig,et al.  Brain electric microstates and momentary conscious mind states as building blocks of spontaneous thinking: I. Visual imagery and abstract thoughts. , 1998, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[40]  P. Maes.  How to Do the Right Thing , 1989 .

[41]  Lee McCauley,et al.  A large-scale multi-agent system for navy personnel distribution , 2002, Connect. Sci..

[42]  Humberto R. Maturana,et al.  The organization of the living: A theory of the living organization , 1975 .

[43]  Michael R. Genesereth,et al.  Software agents , 1994, CACM.

[44]  K. A. Ericsson,et al.  Long-term working memory. , 1995, Psychological review.

[45]  Stan Franklin,et al.  Automating human information agents , 2002 .

[46]  Michael T. Cox.  Metacognition in computation: A selected research review , 2005, Artif. Intell..

[47]  Stan Franklin.  Perceptual Memory and Learning : Recognizing , Categorizing , and Relating , 2005 .

[48]  M. D’Esposito.  Working memory. , 2008, Handbook of clinical neurology.

[49]  Victor S. Johnston.  Why We Feel: The Science Of Human Emotions , 1999 .

[50]  Dipankar Dasgupta,et al.  Metacognition in Software Agents Using Classifier Systems , 1998, AAAI/IAAI.

[51]  Stan Franklin,et al.  Autonomous Agents as Embodied Ai , 1997, Cybern. Syst..

[52]  S. Franklin,et al.  Feelings and Emotions as Motivators and Learning Facilitators , 2004 .

[53]  Stevan Harnad.  The Symbol Grounding Problem , 1999, ArXiv.

[54]  H. Maturana,et al.  Autopoiesis and Cognition , 1980 .

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

[56]  Stan Franklin,et al.  Meadow voles, Microtus pennsylvanicus, have the capacity to recall the “what”, “where”, and “when” of a single past event , 2007, Animal Cognition.

[57]  B. Baars.  In the Theater of Consciousness , 1997 .

[58]  B. Baars.  The conscious access hypothesis: origins and recent evidence , 2002, Trends in Cognitive Sciences.

[59]  Pentti Kanerva,et al.  Sparse Distributed Memory , 1988 .

[60]  R. Malach,et al.  When the Brain Loses Its Self: Prefrontal Inactivation during Sensorimotor Processing , 2006, Neuron.

[61]  W. James,et al.  The Principles of Psychology. , 1983 .

[62]  A. Damasio.  The feeling of what happens , 2001 .

[63]  Stan Franklin.  Evolutionary pressures and a stable world for animals and robots: A commentary on Merker , 2005, Consciousness and Cognition.

[64]  B. Merker.  The liabilities of mobility: A selection pressure for the transition to consciousness in animal evolution , 2005, Consciousness and Cognition.

[65]  Stan Franklin,et al.  A "Consciousness"-Based Architecture for a Functioning Mind , 2005 .

[66]  David A. McAllester,et al.  Systematic Nonlinear Planning , 1991, AAAI.

[67]  Frank J. Lee,et al.  Modeling Emotion: Arousal's Impact on Memory , 2006 .

[68]  B. Baars,et al.  How conscious experience and working memory interact , 2003, Trends in Cognitive Sciences.

[69]  Aaron Sloman,et al.  What Sort of Architecture is Required for a Human-Like Agent? , 1999 .