Concepts as Semantic Pointers: A Framework and Computational Model

Abstract

The reconciliation of theories of concepts based on prototypes, exemplars, and theory-like structures is a longstanding problem in cognitive science. In response to this problem, researchers have recently tended to adopt either hybrid theories that combine various kinds of representational structure, or eliminative theories that replace concepts with a more finely grained taxonomy of mental representations. In this paper, we describe an alternative approach involving a single class of mental representations called "semantic pointers." Semantic pointers are symbol-like representations that result from the compression and recursive binding of perceptual, lexical, and motor representations, effectively integrating traditional connectionist and symbolic approaches. We present a computational model using semantic pointers that replicates experimental data from categorization studies involving each prior paradigm. We argue that a framework involving semantic pointers can provide a unified account of conceptual phenomena, and we compare our framework to existing alternatives in accounting for the scope, content, recursive combination, and neural implementation of concepts.

The knowledge level in cognitive architectures: Current limitations and possible developments

“…The SPAUN architecture, assuming this perspective, has been successfully used to replicate three paradigmatic categorization studies concerning prototypebased categorization, exemplar-based categorization and theory-theory based categorization [37]. Such results show that the provided representational approach can account for different kinds of categorization processes assumed in the heterogeneous perspective.…”

Dual PECCS: a cognitive system for conceptual representation and categorization

“…More in detail, Dual-PECCS is equipped with a hybrid knowledge base composed of heterogeneous representations of the same conceptual entities: that is, the hybrid knowledge base includes prototypes, exemplars and classical representations for the same concept. Such different bodies of knowledge act like semantic pointers towards the same conceptual entity (Blouw et al, 2015;Eliasmith et al, 2012;Thagard, 2012). 5…”

“…5 It is worth-noting, however, that the similarity with the semantic pointer perspective is limited to this point. In fact, as pointed out in (Lieto, 2014), while (Blouw et al, 2015;Eliasmith et al, 2012;Thagard, 2012) propose a Both prototypes and exemplars are represented by adopting the conceptual spaces framework (see Section 3.1), while classical information is represented through standard symbolic formalisms (i.e., by means of a formal ontology).…”

Exploring Semantic Relatedness in Arabic Corpora using Paradigmatic and Syntagmatic Models

“…Each time a word is encountered in the corpus, its memory vector is updated with context information provided through the superposition of the environmental vectors for every other word in the surrounding sentence [4]. To Represent order information about the word, BEAGLE and RPM bind together collections of environmental Vectors into order vectors that are added to memory vectors during training [16].…”

“…[21]. Functionally, the two approaches are quite similar, but random permutation is much more computationally efficient than convolution [4].…”