Simulating and predicting dynamical systems with spatial semantic pointers
| Autor: | Peter Blouw, Aaron R. Voelker, Xuan Choo, Terrence C. Stewart, Nicole Sandra-Yaffa Dumont, Chris Eliasmith |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Structure (mathematical logic)
Theoretical computer science Artificial neural network Dynamical systems theory Spacetime Exploit Computer science Cognitive Neuroscience Cognition 02 engineering and technology Topological space 03 medical and health sciences Range (mathematics) 0302 clinical medicine Arts and Humanities (miscellaneous) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 030217 neurology & neurosurgery |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|