Parallel Distributed Processing: Implications for Cognition and Development

By James L. McClelland. 1988

Subfields: Cognitive Science & Psychology

How researchers see this paper

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

In Cognitive Science & Psychology

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, background): “This approach has shown that neural networks can behave as if they learned explicitly structured knowledge, such as a rule for producing the past tense of words (Rumelhart & McClelland, 1986), rules for solving simple balance-beam physics problems (McClelland, 1988), or a tree to represent types of ”
Rethinking eliminative connectionism. (1998, methodology): “Another important, influential model is the model of the development of children's understanding of the balancebeam by McClelland (1989), which Shultz et al. (1995) described as ''the pioneering attempt to apply modern connectionist techniques to developmental problem solving tasks.''”
On the control of automatic processes: a parallel distributed processing account of the Stroop effect. (1990, methodology): “For example, McClelland (1979) presented a multilevel PDP system that provided an account of the time course of psychological processes; however, this system did not include a learning algorithm.”
On the nature and origin of intuitive theories : learning, physics and psychology (2015, background): “What was previously seen as the discrete acquisition of a new basic understanding of some concept or the relationship between concepts [114, 139, 117, 138].”
Connectionist Models in Developmental Cognitive Neuroscience : Critical Periods and the Paradox of Success (2005, background): “Both are quasiregular (Seidenberg & McClelland, 1989): they are dominated by rule-like regularities but admit forms that deviate from these central tendencies in differing degrees; the " exceptions " partially overlap with the rule-governed forms and so are rarely arbitrary; the deviant forms tend…”
The Developmental Course of Distance, Time, and Velocity Concepts:A Generative Connectionist Model (2000, background): “Some researchers have argued that weight adjustment alone is capable of stage transition (McClelland, 1989; Plunkett & Sinha, 1992).”
Précis of Semantic Cognition: A Parallel Distributed Processing Approach (2008, background): “Our current work grows in part out of a long-standing effort to apply the PDP framework to aspects of cognitive development (McClelland 1989; 1994; Munakata & McClelland 2003).”
Connectionist models of cognitive development: where next? (2005, background): “Stage-like effects in learning the balance-beam problem can be shown to arise naturally in neural networks as a consequence of simple nonlinearities in the response functions of processing units, because small quantitative changes in a learning system can lead to qualitative changes in behavior [ 17”
Semantic Cognition: A Parallel Distributed Processing Approach (2004, background): “Predictive error-driven learning is the engine that drives knowledge acquisition and representational change in many PDP models of cognitive development, including an early model (McClelland, 1989) of children’s understanding of balance scales (Inhelder & Piaget, 1958; Siegler, 1976); several simple”
Rethinking infant knowledge: toward an adaptive process account of successes and failures in object permanence tasks. (1997, methodology): “A concrete instantiation of this idea was presented in a model of the control of adaptive processing systems by Cohen, Dunbar, and McClelland (1990). The model was applied to performance in the Stroop task, in which a color word (e.”