Semantic Cognition: A Parallel Distributed Processing Approach

By Timothy T. Rogers, James L. McClelland. 2004

1,118 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Natural Language Processing, Representation & Self-Supervised Learning

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 Experimental and Cognitive Psychology

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Grounded Language Learning in a Simulated 3D World (2017, background): “Another key requirement for linguistic generalisation is the ability to extend category terms beyond the speciﬁc exemplars from which those concepts were learned (Quinn et al., 1993; Rogers and McClelland, 2004).”
Distributional Memory: A General Framework for Corpus-Based Semantics (2010, neutral): “For a recent extended example of this approach, see Rogers and McClelland (2004).”
A mathematical theory of semantic development in deep neural networks (2018, background): “Given the SVD of the training set’s input–output correlation matrix in [4], we can now explicitly describe the network’s learning dynamics.”
Learning to Make Analogies by Contrasting Abstract Relational Structure (2019, background): “Many of the most important studies of analogy in AI involve symbolic or numerical patterns (Hof-stadter, 1996), and various neural models of semantic cognition more generally also operate on discrete, feature-based representations of input concepts (Rogers & McClelland, 2004; Devereux et al., 2018).”
Learning by Abstraction: The Neural State Machine (2019, background): “…adept at making abstractions of various kinds: We make analogies and form concepts to generalize from given instances to unseen examples [70]; we see things in context, and build compositional world models to represent objects and understand their interactions and subtle relations,…”
Semantic feature production norms for a large set of living and nonliving things (2005, background): “In addition, Rogers and McClelland (2004) have outlined feature-based explanations for a number of phenomena that have been cited as evidence for knowledge-based theories.”
Précis of Semantic Cognition: A Parallel Distributed Processing Approach (2008, background): “For example, we agree with theory theorists that "semantic knowledge" encompasses more than just list-like knowledge about the properties of objects—it includes knowledge about how objects interact with one another, how certain properties and situations give rise to other properties and situations, ”
Understanding Grounded Language Learning Agents (2017, background): “Neuroscientiﬁc theories of memory, representation and learning have been developed to account for these effects (Rogers & McClelland, 2004; Binder & Desai, 2011).”
Learning hierarchical categories in deep neural networks (2013, methodology): “To begin, though, we consider the case of orthogonal input representations where each item is designated by a single active input unit, as used by (Rumelhart & Todd, 1993) and (Rogers & McClelland, 2004).”
Memory as a Constructive Process: The Parallel Distributed Processing Approach (2010, neutral): “Subsequent work with Tim Rogers, presented in our 2004 book, Semantic Cognition, focused on the other, gradual developmental learning system located in other regions of the neocortex (5).”
Statistical mechanics of complex neural systems and high dimensional data (2013, methodology): “] using single pixel camera [40, 41] technology. Also diverse applications of these same techniques to neuronal information processing are discussed in [30], including semantic information processing [42, 43, 44], short-term memory [45, 46], neural circuits for L1 minimization [47], learning sparse ”
Complementary learning systems within the hippocampus: A neural network modeling approach to reconciling episodic memory with statistical learning (2016, background): “This is because there was enough exposure for CA1 to learn representations with its slower learning rate, and because distributed, overlapping representations are highly sensitive to frequency statistics over time (26).”
Integration of New Information in Memory: New Insights from a Complementary Learning Systems Perspective (2020, background): “(See [20] for evidence of similar patterns in young children as well as other characteristic patterns exhibited both by developing children and the network).”
Both the Middle Temporal Gyrus and the Ventral Anterior Temporal Area Are Crucial for Multimodal Semantic Processing: Distortion-corrected fMRI Evidence for a Double Gradient of Information Convergence in the Temporal Lobes (2012, result): “These results relate directly to those computational models of semantic memory, which suggest that (1) the semantic system includes a modality-invariant hub, which extracts pan-modal statistical structure from modalityspecific regions (Lambon Ralph et al., 2010; Pobric et al., 2010b; Patterson et al”
A Survey of Statistical Network Models (2009, neutral): “, Rogers and McClelland [257]).”
What does theoretical neuroscience have to offer the study of behavioral development?:Insights from a dynamic field theory of spatial cognition (2007, background): “Because such models are often loosely tied to behavior, they can become demonstration proofs of the power of synaptic changes over learning rather than formal theories of particular types of developmental change (see Rogers & McClelland, 2004, for an exception).”