Linking Neural and Symbolic Representation and Processing of Conceptual Structures

We compare and discuss representations in two cognitive architectures aimed at representing and processing complex conceptual (sentence-like) structures. First is the Neural Blackboard Architecture (NBA), which aims to account for representation and processing of complex and combinatorial conceptual structures in the brain. Second is IDyOT (Information Dynamics of Thinking), which derives sentence-like structures by learning statistical sequential regularities over a suitable corpus. Although IDyOT is designed at a level more abstract than the neural, so it is a model of cognitive function, rather than neural processing, there are strong similarities between the composite structures developed in IDyOT and the NBA. We hypothesize that these similarities form the basis of a combined architecture in which the individual strengths of each architecture are integrated. We outline and discuss the characteristics of this combined architecture, emphasizing the representation and processing of conceptual structures.

[1]  Geraint A. Wiggins,et al.  Entraining IDyOT: Timing in the Information Dynamics of Thinking , 2016, Front. Psychol..

[2]  Z. Harris,et al.  Foundations of language , 1941 .

[3]  Chilin Shih,et al.  A Stochastic Finite-State Word-Segmentation Algorithm for Chinese , 1994, ACL.

[4]  Geraint A. Wiggins,et al.  IDyOT: A Computational Theory of Creativity as Everyday Reasoning from Learned Information , 2015 .

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

[6]  Arash Eshghi,et al.  Probabilistic induction for an incremental semantic grammar , 2013, IWCS.

[7]  Thomas L. Griffiths,et al.  Supplementary Information for Natural Speech Reveals the Semantic Maps That Tile Human Cerebral Cortex , 2022 .

[8]  Z. Harris,et al.  Foundations of Language , 1940 .

[9]  Peter Gärdenfors,et al.  Applications of conceptual spaces : the case for geometric knowledge representation , 2015 .

[10]  Judea Pearl,et al.  Bayesian Networks , 1998, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[11]  Ian H. Witten,et al.  Multiple viewpoint systems for music prediction , 1995 .

[12]  Antonio Chella,et al.  A Cognitive Architecture for Music Perception Exploiting Conceptual Spaces , 2015 .

[13]  N. Foo.  Conceptual Spaces—The Geometry of Thought , 2022 .

[14]  Frank van der Velde,et al.  Learning of control in a neural architecture of grounded language processing , 2010, Cognitive Systems Research.

[15]  Marc de Kamps,et al.  The necessity of connection structures in neural models of variable binding , 2015, Cognitive neurodynamics.

[16]  Frank van der Velde,et al.  Concepts and Relations in Neurally Inspired In Situ Concept-Based Computing , 2016, Front. Neurorobot..

[17]  Michael R. Brent,et al.  An Efficient, Probabilistically Sound Algorithm for Segmentation and Word Discovery , 1999, Machine Learning.

[18]  Frank van der Velde,et al.  Learning Sequential Control in a Neural Blackboard Architecture for In Situ Concept Reasoning , 2016, NeSy@HLAI.

[19]  Geraint A. Wiggins,et al.  Principles of structure building in music, language and animal song , 2015, Philosophical Transactions of the Royal Society B: Biological Sciences.

[20]  Geraint A. Wiggins,et al.  Auditory Expectation: The Information Dynamics of Music Perception and Cognition , 2012, Top. Cogn. Sci..

[21]  Salvatore Gaglio,et al.  A cognitive architecture for robot self-consciousness , 2008, Artif. Intell. Medicine.

[22]  Ignazio Infantino,et al.  IMITATION LEARNING AND ANCHORING THROUGH CONCEPTUAL SPACES , 2007, Appl. Artif. Intell..

[23]  Geraint A. Wiggins,et al.  The Role of Expectation and Probabilistic Learning in Auditory Boundary Perception: A Model Comparison , 2010, Perception.

[24]  D. Corkill.  Blackboard Systems , 1991 .

[25]  J. Cowan,et al.  Excitatory and inhibitory interactions in localized populations of model neurons. , 1972, Biophysical journal.

[26]  Frank van der Velde,et al.  Communication, concepts and grounding , 2015, Neural Networks.

[27]  Arthur M. Young,et al.  The geometry of meaning , 1976 .

[28]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[29]  Geraint A. Wiggins.  ‘‘I let the music speak’’: Cross-domain application of a cognitive model of musical learning , 2011 .

[30]  Charles Kemp,et al.  How to Grow a Mind: Statistics, Structure, and Abstraction , 2011, Science.

[31]  Martin Schmettow,et al.  A Semantic Map for Evaluating Creativity , 2015, ICCC.

[32]  Marcus T. Pearce,et al.  The construction and evaluation of statistical models of melodic structure in music perception and composition , 2005 .

[33]  Matthew Purver,et al.  From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation , 2015, J. Artif. Gen. Intell..

[34]  Aaron Sloman,et al.  The Altricial-Precocial Spectrum for Robots , 2005, IJCAI.

[35]  Geraint A. Wiggins,et al.  Methods for Combining Statistical Models of Music , 2004, CMMR.

[36]  Frank van der Velde,et al.  Combinatorial Structures and Processing in Neural Blackboard Architectures , 2015, CoCo@NIPS.

[37]  Steven M Frankland,et al.  An architecture for encoding sentence meaning in left mid-superior temporal cortex , 2015, Proceedings of the National Academy of Sciences.

[38]  F. van der Velde,et al.  Neural blackboard architectures of combinatorial structures in cognition , 2006, Behavioral and Brain Sciences.

[39]  Franz Aurenhammer,et al.  Voronoi diagrams—a survey of a fundamental geometric data structure , 1991, CSUR.

[40]  Geraint A. Wiggins.  The Mind’s Chorus: Creativity Before Consciousness , 2012, Cognitive Computation.

[41]  Ian H. Witten,et al.  PREDICTION AND ENTROPY OF MUSIC , 1990 .

[42]  R. Shepard.  Circularity in Judgments of Relative Pitch , 1964 .

[43]  Geraint A. Wiggins,et al.  Mind the gap: an attempt to bridge computational and neuroscientific approaches to study creativity , 2014, Front. Hum. Neurosci..

[44]  Joshua B. Tenenbaum,et al.  Building machines that learn and think like people , 2016, Behavioral and Brain Sciences.

[45]  R. Quiroga.  Concept cells: the building blocks of declarative memory functions , 2012, Nature Reviews Neuroscience.