Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience

By Ross W. Gayler. 2004

329 citations recorded by the source corpus.

Jackendoff (2002) posed four challenges that linguistic combinatoriality and rules of language present to theories of brain function. The essence of these problems is the question of how to neurally instantiate the rapid construction and transformation of the compositional structures that are typically taken to be the domain of symbolic processing. He contended that typical connectionist approaches fail to meet these challenges and that the dialogue between linguistic theory and cognitive neuroscience will be relatively unproductive until the importance of these problems is widely recognised and the challenges answered by some technical innovation in connectionist modelling. This paper claims that a little-known family of connectionist models (Vector Symbolic Architectures) are able to meet Jackendoff's challenges.

Subfields: Artificial Intelligence, Cognitive Neuroscience

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

Citations in the corpus

Constrained Few-shot Class-incremental Learning (2022, background): “This critical requirement can be met by exploiting hyperdimensional computing [10, 19, 35], where classes can be represented by random high-dimensional vectors with a dimensionality in the order of thousands.”
Biologically Plausible, Human-scale Knowledge Representation (2016, background): “The final approach we consider is the class of proposals broadly called conjunctive coding approaches, or, more recently, Vector Symbolic Architectures (VSAs; (Gayler, 2003)).”
Resonator Networks, 1: An Efficient Solution for Factoring High-Dimensional, Distributed Representations of Data Structures (2020, background): “A family of models called vector symbolic architectures (VSAs) encodes these structures into distributed representations, providing a framework that can reconcile the symbolic and connectionist perspectives (Plate, 2003; Gayler, 2003; Kanerva, 2009).”
Generalized Key-Value Memory to Flexibly Adjust Redundancy in Memory-Augmented Networks (2022, unknown): “The distinctive feature of the MANN architecture in [12] is that the neural network is guided to produce support vectors in the form of d -dimensional vectors with the properties suitable for hyperdimensional computing [13], [15] (also known as vector symbolic architectures [16], [17]).”