Attractor Networks

Artificial neural networks (ANNs), sometimes referred to as connectionist networks, are computational models based loosely on the neural architecture of the brain. Over the past twenty years, ANNs have proven to be a fruitful framework for modeling many aspects of cognition, including perception, attention, learning and memory, language, and executive control. A particular type of ANN, called an attractor network, is central to computational theories of consciousness, because attractor networks can be analyzed in terms of properties—such as temporal stability, and strength, quality, and discreteness of representation— that have been ascribed to conscious states. Some theories have gone so far as to posit that attractor nets are the computational substrate from which conscious states arise.

[1]  A. Marcel.  Conscious and unconscious perception: An approach to the relations between phenomenal experience and perceptual processes , 1983, Cognitive Psychology.

[2]  Geoffrey E. Hinton,et al.  Schemata and Sequential Thought Processes in PDP Models , 1986 .

[3]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

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

[5]  M J Farah,et al.  Dissociated overt and covert recognition as an emergent property of a lesioned neural network. , 1993, Psychological review.

[6]  Michael C. Mozer,et al.  On the Computational Utility of Consciousness , 1994, NIPS.

[7]  John R. Searle,et al.  The Rediscovery of the Mind , 1995, Artif. Intell..

[8]  Donald W. Mathis,et al.  Conscious and unconscious perception: A computational theory , 1996 .

[9]  J. G. Taylor,et al.  Cortical Activity and the Explanatory Gap , 1998, Consciousness and Cognition.

[10]  S. Grossberg.  The Link between Brain Learning, Attention, and Consciousness , 1999, Consciousness and Cognition.

[11]  G. Rees,et al.  Covariation of activity in visual and prefrontal cortex associated with subjective visual perception. , 1999, Proceedings of the National Academy of Sciences of the United States of America.

[12]  Richard S. Zemel,et al.  Localist Attractor Networks , 2001, Neural Computation.

[13]  Y. Munakata.  Graded representations in behavioral dissociations , 2001, Trends in Cognitive Sciences.

[14]  S. Dehaene,et al.  Towards a cognitive neuroscience of consciousness: basic evidence and a workspace framework , 2001, Cognition.

[15]  R. French,et al.  Implicit learning and consciousness: A graded, dynamic perspective , 2002 .