Unsupervised Multi-net Simulation: An Application to Child Development

We propose a gated multi-net system that simulates the transition of child language from the one-word stage to the two-word stage. In this system, a modified counterpropagation network simulates child language at the one-word stage, whilst an unsupervised temporal neural network simulates child language at the two-word stage. During simulation, inputs encoding the perceptual and conceptual features of events a child is likely to speak about are simultaneously applied to the two networks. Initially, the system is predisposed to outputting one-word utterances, but as the simulation proceeds, a gating mechanism predisposes the system to output two-word utterances. The system exhibits a gradual transition from one-word utterances to two-word utterances similar to that observed in children undergoing the same transitional phase.

[1]  Elissa L. Newport,et al.  Chapter 1 The Invention of Language by Children: Environmental and Biological Influences on the Acquisition of Language , 2005 .

[2]  Edward E. Smith,et al.  An Invitation to cognitive science , 1997 .

[3]  B. MacWhinney.  The CHILDES project: tools for analyzing talk , 1992 .

[4]  Chris Sinha,et al.  Symbol Grounding or the Emergence of Symbols? Vocabulary Growth in Children and a Connectionist Net , 1992 .

[5]  B. MacWhinney,et al.  Implementations are not conceptualizations: Revising the verb learning model , 1991, Cognition.

[6]  D. Mareschal,et al.  Modeling Infant Speech Sound Discrimination Using Simple Associative Networks. , 2001, Infancy : the official journal of the International Society on Infant Studies.

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

[8]  T. Sejnowski,et al.  Irresistible environment meets immovable neurons , 1997, Behavioral and Brain Sciences.

[9]  James L. McClelland.  Parallel Distributed Processing: Implications for Cognition and Development , 1988 .

[10]  S. Grossberg.  Some Networks That Can Learn, Remember, and Reproduce any Number of Complicated Space-Time Patterns, I , 1969 .

[11]  M. Tomasello,et al.  Joint attention on actions: acquiring verbs in ostensive and non-ostensive contexts , 1992, Journal of Child Language.

[12]  Michael I. Jordan,et al.  A Competitive Modular Connectionist Architecture , 1990, NIPS.

[13]  Ping Li,et al.  PatPho: A phonological pattern generator for neural networks , 2002, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[14]  K. Nelson,et al.  Structure and strategy in learning to talk. , 1973 .

[15]  Gert Westermann,et al.  Modelling Cognitive Development with Constructivist Neural Networks , 2000, NCPW.

[16]  D. Ingram.  First Language Acquisition: Method, Description and Explanation , 1989 .

[17]  Lois Bloom,et al.  One Word at a Time: The Use of Single Word Utterances Before Syntax , 1976 .

[18]  Syed Sibte Raza Abidi,et al.  Conglomerate'Neural Network Architectures: The Way Ahead for Simulating Early Language Development , 1997, J. Inf. Sci. Eng..

[19]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

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

[21]  S. Crain,et al.  Language Acquisition , 2008 .

[22]  Elissa L. Newport,et al.  The invention of language by children: Environmental and biological influences , 2002 .

[23]  Kim Plunkett,et al.  Language Acquisition and Connectionism. , 1998 .

[24]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[25]  Kim Plunkett,et al.  Theories of early language acquisition , 1997, Trends in Cognitive Sciences.

[26]  Mark S. Seidenberg,et al.  Rules or connections? The past tense revisited , 1992 .

[27]  V. Marchman,et al.  U-shaped learning and frequency effects in a multi-layered perception: Implications for child language acquisition , 1991, Cognition.

[28]  John H. Flavell,et al.  Stage-related properties of cognitive development , 1971 .

[29]  Michael S. C. Thomas,et al.  Connectionist Models of Development, Developmental Disorders and Individual Differences Pre-existing Theoretical Claims , 2022 .

[30]  P. Ladefoged.  A course in phonetics , 1975 .

[31]  R. Brown,et al.  A First Language , 1973 .

[32]  Raymond J. Mooney,et al.  Induction of First-Order Decision Lists: Results on Learning the Past Tense of English Verbs , 1995, J. Artif. Intell. Res..

[33]  Kim Plunkett,et al.  Evolution of a Rapidly Learned Representation for Speech , 1998, CoNLL.

[34]  Shun-ichi Amari,et al.  Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements , 1972, IEEE Transactions on Computers.

[35]  A. Karmiloff-Smith,et al.  Modelling typical and atypical cognitive development , 2002 .

[36]  Abel Nyamapfene,et al.  Unsupervised multimodal neural networks , 2006 .

[37]  J. Elman.  Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[38]  Thomas R. Shultz,et al.  Modeling cognitive development on balance scale phenomena , 1994, Machine Learning.

[39]  V. Marchman,et al.  Learning from a connectionist model of the acquisition of the English past tense , 1996, Cognition.

[40]  B. MacWhinney.  Models of the emergence of language. , 1998, Annual review of psychology.