Simulating and Predicting Dynamical Systems With Spatial Semantic Pointers

Neural Computation, 2021

Aaron R. Voelker, Peter Blouw, Xuan Choo, Nicole Sandra-Yaffa Dumont, Terrence C. Stewart, Chris Eliasmith

Abstract

While neural networks are highly effective at learning task-relevant representations from data, they typically do not learn representations with the kind of symbolic structure that is hypothesized to support high-level cognitive processes, nor do they naturally model such structures within problem domains that are continuous in space and time. To fill these gaps, this work exploits a method for defining vector representations that bind discrete (symbol-like) entities to points in continuous topological spaces in order to simulate and predict the behavior of a range of dynamical systems. These vector representations are spatial semantic pointers (SSPs), and we demonstrate that they can (1) be used to model dynamical systems involving multiple objects represented in a symbol-like manner and (2) be integrated with deep neural networks to predict the future of physical trajectories. These results help unify what have traditionally appeared to be disparate approaches in machine learning.

Full text links

 PDF

 DOI

Journal Article

Doi
10.1162/neco_a_01410
Journal
Neural Computation
Month
07
Volume
33
Number
8
Pages
2033-2067
Publisher
MIT Press

Cite

Plain text

BibTeX