Simulation of Quantification Abilities Using a Modular Neural Network Approach

A novel modular neural network architecture and its application to the field of numerical cognition simulation are presented. Previous modular connectionist systems are typically constrained at one of two levels: at the representational level, in that the connectivity of the modules is hard-wired by the modeller; or at a local architectural level, in that the modeller explicitly allocates each module to a specific subtask. Our approach aims to minimise the constraints, thus reducing the bias possibly introduced by the modeller. The efficacy of this approach is demonstrated through the successful simulation of the development of two quantification abilities, subitising and counting, amongst children. It is concluded that such a minimally constrained modular system may contribute to both the capturing of learnt behaviour, and the allocation of modules to subtasks according to the nature of the task.

[1]  Kim Plunkett,et al.  Developing object permanence: A connectionist model , 1995 .

[2]  James A. Anderson,et al.  An Introduction To Neural Networks , 1998 .

[3]  Teuvo Kohonen.  Notes on Neural Computing , 1988 .

[4]  N. K. Bose,et al.  Neural Network Fundamentals with Graphs, Algorithms and Applications , 1995 .

[5]  S E Antell,et al.  Perception of numerical invariance in neonates. , 1983, Child development.

[6]  Daniel J. Amit,et al.  Modeling brain function: the world of attractor neural networks, 1st Edition , 1989 .

[7]  Alfonso Caramazza,et al.  Cognitive mechanisms in number processing and calculation: Evidence from dyscalculia , 1985, Brain and Cognition.

[8]  C. Gallistel,et al.  Preverbal and verbal counting and computation , 1992, Cognition.

[9]  Henrik Gollee,et al.  Modular Neural Networks and Self-Decomposition , 1997 .

[10]  Alexander H. Waibel,et al.  The Meta-Pi Network: Building Distributed Knowledge Representations for Robust Multisource Pattern Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  J. Elman,et al.  Rethinking Innateness: A Connectionist Perspective on Development , 1996 .

[12]  Jamie I. D. Campbell.  The Nature and origins of mathematical skills , 1992 .

[13]  ROBERT S. MOYER,et al.  Time required for Judgements of Numerical Inequality , 1967, Nature.

[14]  D J Amit,et al.  Neural networks counting chimes. , 1988, Proceedings of the National Academy of Sciences of the United States of America.

[15]  John Richards,et al.  The Acquisition and Elaboration of the Number Word Sequence , 1982 .

[16]  R. Hecht-Nielsen.  Counterpropagation networks. , 1987, Applied optics.

[17]  James A. Anderson.  Mental arithmetic using neural networks , 1998 .

[18]  Jaap Hoekstra.  Counting With Artificial Neural Networks: An Experiment , 1992 .

[19]  Nils J. Nilsson,et al.  Learning Machines: Foundations of Trainable Pattern-Classifying Systems , 1965 .

[20]  E. Spelke.  Initial knowledge: six suggestions , 1994, Cognition.

[21]  Stanislas Dehaene,et al.  Development of Elementary Numerical Abilities: A Neuronal Model , 1993, Journal of Cognitive Neuroscience.

[22]  James L. McClelland,et al.  On learning the past-tenses of English verbs: implicit rules or parallel distributed processing , 1986 .

[23]  R. Gelman,et al.  The Child's Understanding of Numbers , 1979 .

[24]  S. Dehaene.  Varieties of numerical abilities , 1992, Cognition.

[25]  C. Gallistel,et al.  The Child's Understanding of Number , 1979 .

[26]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[27]  Michael I. Jordan,et al.  Task Decomposition through Competition in A , 1990 .

[28]  K. Fuson.  Children's Counting and Concepts of Number , 1987 .

[29]  L. E. Krueger.  Reconciling Fechner and Stevens: Toward a unified psychophysical law , 1989, Behavioral and Brain Sciences.

[30]  V. Marchman,et al.  From rote learning to system building: acquiring verb morphology in children and connectionist nets , 1993, Cognition.

[31]  E. Spelke,et al.  Detection of intermodal numerical correspondences by human infants. , 1983, Science.

[32]  Thomas R. Shultz,et al.  Modeling cognitive development with a generative connectionist algorithm , 1995 .

[33]  S. Dehaene,et al.  Cross-linguistic regularities in the frequency of number words , 1992, Cognition.

[34]  S. Dehaene,et al.  The Number Sense: How the Mind Creates Mathematics. , 1998 .

[35]  M. McCloskey,et al.  Chapter 10 Mathnet: Preliminary Results From A Distributed Model Of Arithmetic Fact Retrieval , 1992 .