Vector-Derived Transformation Binding: An Improved Binding Operation for Deep Symbol-Like Processing in Neural Networks

Neural Computation, 2019

Jan Gosmann, Chris Eliasmith

Abstract

We present a new binding operation, vector-derived transformation binding (VTB), for use in vector symbolic architectures (VSA). The performance of VTB is compared to circular convolution, used in holographic reduced representations (HRRs), in terms of list and stack encoding capacity. A special focus is given to the possibility of a neural implementation by the means of the Neural Engineering Framework (NEF). While the scaling of required neural resources is slightly worse for VTB, it is found to be on par with circular convolution for list encoding and better for encoding of stacks. Furthermore, VTB influences the vector length less, which also benefits a neural implementation. Consequently, we argue that VTB is an improvement over HRRs for neurally implemented VSAs.

Full text links

 PDF

 External link

 DOI

Journal Article

Doi
10.1162/neco_a_01179
Journal
Neural Computation
Month
05
Volume
31
Number
5
Pages
849-869
Publisher
MIT Press

Cite

Plain text

BibTeX