Vector Symbolic Architectures answer Jackendoff's challenges for cognitive neuroscience

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.

This is a slightly updated version of the paper presented at the Joint International Conference on Cognitive Science, 13-17 July 2003, University of New South Wales, Sydney, Australia. 6 pages

Cited by in corpus (16)

• Robust High-dimensional Memory-augmented Neural Networks
• Vector Symbolic Architectures as a Computing Framework for Emerging Hardware
• The Importance of Balanced Data Sets: Analyzing a Vehicle Trajectory Prediction Model based on Neural Networks and Distributed Representations
• Exploring Embedding Methods in Binary Hyperdimensional Computing: A Case Study for Motor-Imagery based Brain-Computer Interfaces
• Resonator networks for factoring distributed representations of data structures
• DotHash: Estimating Set Similarity Metrics for Link Prediction and Document Deduplication
• Computing on Functions Using Randomized Vector Representations
• Analyzing the Capacity of Distributed Vector Representations to Encode Spatial Information
• Towards a Predictive Processing Implementation of the Common Model of Cognition
• Theory of the superposition principle for randomized connectionist representations in neural networks
• Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computing
• Cellular Automata Can Reduce Memory Requirements of Collective-State Computing
• Recursive Sketches for Modular Deep Learning
• High-dimensional distributed semantic spaces for utterances
• Should Semantic Vector Composition be Explicit? Can it be Linear?
• A crossover code for high-dimensional composition