Early lexical development in a self-organizing neural network

Li, Ping; Farkaš, Igor; MacWhinney, Brian

doi:10.1016/j.neunet.2004.07.004

Cited by 210 publications

(185 citation statements)

References 32 publications

Supporting

Mentioning

176

Contrasting

Unclassified

Order By: Relevance

“…Several computational models have therefore implemented simple learning mechanisms (such as Hebbian rules) to create associations between patterns of active neurons representing the phonological aspects of words and internal simulations (i.e., representations of object features involved in perception and action, cf. Jeannerod, 2007;Mayor & Plunkett, 2010;Caligiore et al, 2010;Li, Farkas, & MacWhinney, 2004).…”

Section: Introductionmentioning

confidence: 99%

Vision, action and language unified through embodiment

Caligiore

Fischer

2012

Psychological Research

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Vision, action and language unified through embodiment

Caligiore

Fischer

2012

Psychological Research

View full text Add to dashboard Cite

“…The most common unsupervised algorithm is Hebbian learning, which is often used to train selforganizing maps (e.g., Cohen et al, 2002;Li et al, 2004Li et al, , 2007. Hebbian learning strengthens the weight between two units whose activity is correlated and weakens the weight between two units whose activity is uncorrelated.…”

Section: Issues In Modeling Changes In Experiencementioning

confidence: 99%

“…This is akin to the processes of synaptogenesis and pruning: The former forms some maximum number of synapses in early childhood, and the latter eliminates unnecessary synapses to eventually settle at adult levels (Huttenlocher & Dabholkar, 1997). Another example of the use of self-organizing maps to model neural plasticity can be found in models of language acquisition by Li et al (2004) and Farkas and Li (2002).A final way in which neural plasticity has been modeled is through the manual addition of hidden units in a static network. In contrast to cascade-correlation frameworks, which recruit additional hidden units as training proceeds, this approach involves the use of different model structures at different ages.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Connectionist modeling of developmental changes in infancy: Approaches, challenges, and contributions.

Yermolayeva¹,

Rakison²

2014

Psychological Bulletin

View full text Add to dashboard Cite

Connectionist models have been applied to many phenomena in infant development including perseveration, language learning, categorization, and causal perception. In this article, we discuss the benefits of connectionist networks for the advancement of theories of early development. In particular, connectionist models contribute novel testable predictions, instantiate the theorized mechanism of change, and create a unifying framework for understanding infant learning and development. We relate these benefits to the 2 primary approaches used in connectionist models of infant development. The first approach employs changes in neural processing as the basis for developmental changes, and the second employs changes in infants' experiences. The review sheds light on the unique hurdles faced by each approach as well as the challenges and solutions related to both, particularly with respect to the identification of critical model components, parameter specification, availability of empirical data, and model comparison. Finally, we discuss the future of modeling work as it relates to the study of development. We propose that connectionist networks stand to make a powerful contribution to the generation and revision of theories of early child development. Furthermore, insights from connectionist models of early development can improve the understanding of developmental changes throughout the life span. Keywords: connectionist modeling, neural network modeling, parallel distributed processing, infant developmentSince the groundbreaking work of Rumelhart and McClelland in the 1980s, there has been an increasing interest in and research on the application of connectionist models to early human development. Connectionist models are instantiations of theories about the mechanisms that underpin particular behaviors. Building computational models allows for the exploration of the interaction of numerous factors both internal and external to the organism that typically contribute to a behavior, which often can be too complex to specify through verbal theory alone . These computational models provide researchers with a number of ways to explicitly test theoretical assumptions and develop novel and testable predictions.However, in our view, for many developmental scientists the contribution of models to an integrated understanding of development is far from clear. Although a given model might provide output that is similar to the behavior of infants, it often remains to be seen whether the model's results and the behavioral results occur for the same reasons. For example, a network may simulate effectively infants' ability to discriminate between two objects that differ along multiple features, but it is possible that the features used by the network for discrimination are different from those used by infants. Computational models have also been criticized for using overly technical terms and notations that may be offputting to nonexperts (Klahr, 2004); for not being explicit about the source of their starting states (Oakes, Newcom...

show abstract

“…Note that algorithms for inducing part of speech categories from raw data (i.e., unsupervised POS tagging) abound, both in the cognitive linguistic literature (e.g., Li et al [37] and references therein) and in the computational linguistic literature (e.g., Banko and Moore [5], Smith and Eisner [56]). …”

Section: Computational Grammar Inductionmentioning

confidence: 99%

Computational Models of Language Acquisition

Wintner

2010

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

Abstract. Child language acquisition, one of Nature's most fascinating phenomena, is to a large extent still a puzzle. Experimental evidence seems to support the view that early language is highly formulaic, consisting for the most part of frozen items with limited productivity. Fairly quickly, however, children find patterns in the ambient language and generalize them to larger structures, in a process that is not yet well understood. Computational models of language acquisition can shed interesting light on this process. This paper surveys various works that address language learning from data; such works are conducted in different fields, including psycholinguistics, cognitive science and computer science, and we maintain that knowledge from all these domains must be consolidated in order for a well-informed model to emerge. We identify the commonalities and differences between the various existing approaches to language learning, and specify desiderata for future research that must be considered by any plausible solution to this puzzle.

show abstract

Early lexical development in a self-organizing neural network

Cited by 210 publications

References 32 publications

Vision, action and language unified through embodiment

Vision, action and language unified through embodiment

Connectionist modeling of developmental changes in infancy: Approaches, challenges, and contributions.

Computational Models of Language Acquisition

Contact Info

Product

Resources

About