The parallel distributed processing approach to semantic cognition

By James L. McClelland, Timothy T. Rogers. 2003

682 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Developmental and Educational Psychology

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 Cognitive Neuroscience

In Developmental and Educational Psychology

Citations in the corpus

Generative Continual Concept Learning (2019, background): “Work on semantic cognition within the PDP framework hypothesizes that abstract semantic concepts are formed in higher level layers of the nervous system (McClelland and Rogers 2003; Saxe, McClelland, and Ganguli 2019).”
Meditation and the neuroscience of consciousness (2007, background): “…contemplative practices resonate with widely accepted developmental models of basic cognitive processes; according to these models, cognitive functions are skills that critically depend upon learning from environmental input (e.g., McClelland & Rogers, 2003; Saffran, Aslin, & Newport, 1996).”
Learning Transferable Knowledge Through Embedding Spaces (2019, methodology): “Works within Parallel Distributed Processing (PDP) framework suggest that embedding spaces can be used to model cognitive processes as cognition is a result of representing data using synaptic connections that are changed based on experiences [8].”
Neuroscience-Inspired Artificial Intelligence. (2017, background): “Elsewhere, neuroscience-inspired analyses of linearized networks have uncovered important principles that may be of general beneﬁt in optimizing learning these networks, and understanding the beneﬁts of network depth and representational structure (McClelland and Rogers, 2003; Saxe et al., 2013).”
Perisylvian language networks of the human brain (2005, result): “An alternative “connectionist” account has been proposed in which linguistic functions are conceived as resulting from parallel distributed processing performed by distributed groups of connected neurons rather than individual centers.(50,51) Although tractography evidence alone cannot distinguish b”
Coarse scales are sufﬁcient for efﬁcient categorization of emotional facial expressions: Evidence from neural computation (neutral): “Dailey et al. [4] used a single layer perceptron in association with the softmax activation function at the level of the output layer, in order to perform non-linear categorization of their images, whereas we used the standard back-propagation algorithm on a multi-layer perceptron [20,31].”
From future self to current action: An identity-based motivation perspective (2018, background): “…self as connected to one’s current self might activate school engagement and working on school might active the idea that the future is near; a process that might unfold through parallel distributed processing (McClelland & Rogers, 2003; Rogers & McClelland, 2005; Rumelhart & McClelland, 1986).”
Neural computation as a tool to differentiate perceptual from emotional processes: the case of anger superiority effect. (2009, neutral): “The goal of the backpropagation network was to create non-linear category borders between the three perceptual categories.”
Structure and deterioration of semantic memory: a neuropsychological and computational investigation. (2004, background): “Items that share few verbal descriptors and which have different visual appearances contribute different inputs and targets to the system, and come to generate differing internal representations (Rumelhart & Todd, 1993; Plaut, 1999; McClelland & Rogers, 2003; Rogers & McClelland, in press).”
Integration of New Information in Memory: New Insights from a Complementary Learning Systems Perspective (2020, background): “Subsequent work [19, 20] showed how this model could account for many aspects of the developmental progression of semantic knowledge acquisition, as well as the disintegration of such knowledge as a function of brain damage, thought to reduce the ﬁdelity of the learned representations of concepts…”
Connectionist models of development (2003, background): “…2001), and how systems can progress from knowing little about the category structure of the world to making fine-grained distinctions between categories and recognizing that different kinds of features are central to different categories (Rogers & McClelland, in press; McClelland & Rogers, 2003).”
Memory as a Constructive Process: The Parallel Distributed Processing Approach (2010, background): “An Integrative Representation Independent of Any Specific Kind of Content? A further feature of our theory is that there should be, somewhere in the neocortex, an area where there is an integrative representation of all sorts of things, encompassing all aspects of their content (9).”
Meditation and the Neuroscience of Consciousness: An Introduction (2007, background): “…2185 743 0c19 CUFX049/Zelazo 0 5 21 85 743 0 printer: cupusbw November 6, 2006 16:32 52 0 the cambridge handbook of consciousness models, cognitive functions are skills that critically depend upon learning from environmental input (e.g., McClelland & Rogers, 2003 ; Saffran, Aslin, & Newport, 1996).”