Connectionist models of development

By Yuko Munakata, James L. McClelland. 2003

203 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/cdaf5597b5df11298e51778fd84674c559cd062a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Developmental and Educational Psychology

In Statistics and Probability

Citations in the corpus

What does theoretical neuroscience have to offer the study of behavioral development?:Insights from a dynamic field theory of spatial cognition (2007, methodology): “…insights about how nonlinear change can emerge from distributed activation in neural networks using relatively simple learning rules (see Munakata & McClelland, 2003, for a review), such models are often weakly linked to the real-time behavior of children in real tasks (see Spencer &…”
Early Speech Perception and Later Language Development: Implications for the "Critical Period" (2005, result): “Furthermore, this view seems to be consistent with dynamic systems views of development (see Munakata & McClelland, 2003).”
Putting Education in “Educational” Apps (2015, background): “Statistical models have revolutionized the way we think about how children and adults learn to make sense of a world full of data (e.g., Brady, Konkle, & Alvarez, 2009; Buchsbaum, Gopnik, Griffiths, & Shafto, 2011; Munakata & McClelland, 2003; Xu & Garcia, 2008).”
The parallel distributed processing approach to semantic cognition (2003, background): “The process is continuous,but there are periods of stability punctuated by relatively rapid transitions also seen in many other developmental models 54,56,59 , reminiscent of the seemingly stage-like character of many aspects of cognitive development 62 .”
Connectionist Models in Developmental Cognitive Neuroscience : Critical Periods and the Paradox of Success (2005, background): “Any summary of the advances achieved within this framework relevant to development (see also Munakata & McClelland, 2003) would have to include the following.”
Finding new facts; thinking new thoughts. (2012, background): “In almost any conventional approach to learning (whether connectionist or Bayesian; McClelland, 1988; Munakata & McClelland, 2003; Ullman et al., 2012), prediction errors inform hypothesis selection.”
A review of methods in the study of attention in autism (2010, background): “The networks are particularly suitable for studying the developmental or learning process since a period of years can be modelled in a short time (Munakata & McClelland, 2003).”
Principles of Learning, Implications for Teaching: A Cognitive Neuroscience Perspective. (2008, background): “This offers one potential mechanism for explaining why it is more difficult to learn a second language later in life (Munakata and McClelland, 2003).”
Word learning emerges from the interaction of online referent selection and slow associative learning (2012, methodology): “By situating learning in connection weights and situation-time processing in changing activation, our approach is broadly consistent with classic connectionist thinking on development (Elman, 1990; Harm & Seidenberg, 1999; Munakata, 1998; Munakata & McClelland, 2003; Munakata et al., 1997).”
Précis of Semantic Cognition: A Parallel Distributed Processing Approach (2008, background): “The following principles capture, however, aspects of the simple model that we believe will prove critical to any such future account; they are considered at length in Rogers and McClelland (2004, Chapter 9). 1. Predictive error-driven learning . Our current work grows in part out of a longstanding ”
The role of frequency in the acquisition of English word order (2005, background): “We would therefore argue that the acquisition of word order, and of the transitive construction, is not a binary affair but is rather an instance of gradually strengthening, graded representations (Mu akata, 2001; Munakata & McClelland, 2003, see alsoDemuth, Machobane, & Moloi, 2003).”