Approaches to cognitive modeling Letting structure emerge : connectionist and dynamical systems approaches to cognition

By James L. McClelland, Matthew Botvinick, D. Noelle, David C. Plaut, Linda B. Smith. 2010

Subfields: Natural Language Processing, 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 Natural Language Processing

In Cognitive Science & Psychology

Citations in the corpus

Environmental drivers of systematicity and generalization in a situated agent (2019, background): “Our results suggest that robust systematic generalisation may be an emergent property of an agent interacting with a rich, situated environment (c.f. McClelland et al., 2010).”
Generalization Through the Recurrent Interaction of Episodic Memories (2012, methodology): “…using error correction algorithms such as backpropagation, are indeed powerful learners of the statistical structure of data sets, for instance comprised of semantic facts (e.g., a robin can fly; McClelland et al., 2010, 1995; McClelland & Rogers, 2003; Rogers & McClelland, 2004; Rumelhart, 1990).”
Bridging Levels of Analysis for Probabilistic Models of Cognition (2012, background): “For example, the recent debate between proponents of probabilistic and connectionist models (Griffiths, Chater, Kemp, Perfors, & Tenenbaum, 2010; McClelland et al., 2010) emphasized that many probabilistic models are defined in terms of structured, discrete representations, such as rules and…”
From simple innate biases to complex visual concepts (2012, methodology): “We selected informative image regions according to mutual information criteria, which often extract a high fraction of class features for natural class (6).”
Building Machines that Learn and Think Like People (2018, background): “These structures are more epiphenomenal than real, emergent properties of more fundamental sub-symbolic cognitive processes (McClelland et al., 2010).”
Seamless Integration and Coordination of Cognitive Skills in Humanoid Robots: A Deep Learning Approach (2017, background): “Here, it is worth noting that artificial neural networks are meant to model the essential features of the nervous system, not its detailed implementation [19]–[21].”
The Computational and Neural Basis of Cognitive Control: Charted Territory and New Frontiers (2014, background): “The second basic tenet of the PDP approach that we will advocate is the dictum that one should avoid stipulating what one seeks to explain (see McClelland et al., 2010; Plaut & McClelland, 2000).”
Bayesian just-so stories in psychology and neuroscience. (2012, background): “Accordingly, it is not clear how a rational analysis carried out at the computational level could shed light on this issue (cf. McClelland et al., 2010).”
Theory learning as stochastic search in the language of thought (2012, background): “…by a network’s weights While emergentist models have been well-received in some areas of development, such as the study of motor and action systems (McClelland et al., 2010), emergentist models of the structure and origins of abstract knowledge (Rogers & McClelland, 2004) have not been widely…”
Emergent Systematic Generalization in a Situated Agent (2019, background): “Because the architecture of our agent does not include components that are explicitly engineered to promote systematicity, we refer to the behaviour it exhibits as emergent systematicity (McClelland et al., 2010).”