Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience

2004/12/13 by Ross W. Gayler, Gayler, Ross W. · 11 citations
Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #Cognitive Science and Education Research #FOS: Computer and information sciences #I.2.0 #I.2.6 #I.5.1 #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function

paper · pdf · doi:10.48550/arxiv.cs/0412059

openalex publication_date 2004/12/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• A Composable Channel-Adaptive Architecture for Seizure Classification
• Encoder-Free Knowledge-Graph Reasoning with LLMs via Hyperdimensional Path Retrieval
• Towards a Comprehensive Theory of Reservoir Computing
• Hey Pentti, We Did (More of) It!: A Vector-Symbolic Lisp With Residue Arithmetic
• Explaining and interpreting hyperdimensional computing classifiers on tabular data
• Exploring Embedding Methods in Binary Hyperdimensional Computing: A Case Study for Motor-Imagery based Brain-Computer Interfaces
• Towards a Predictive Processing Implementation of the Common Model of Cognition
• FactorHD: A Hyperdimensional Computing Model for Multi-Object Multi-Class Representation and Factorization
• A crossover code for high-dimensional composition
• Should Semantic Vector Composition be Explicit? Can it be Linear?
• Vector-Derived Transformation Binding: An Improved Binding Operation for Deep Symbol-Like Processing in Neural Networks

Related

• On the proper treatment of connectionism
• Fodor and Pylyshyn's Critique of Connectionism and the Brain as Basis of the Mind
• The Grand Challenges and Myths of Neural-Symbolic Computation
• Towards a neural architecture of language: Deep learning versus logistics of access in neural architectures for compositional processing
• Perspectives of Neuro--Symbolic Integration – Extended Abstract --