Symmetry and Systematicity

Jeff Mitchell, Jeff Bowers

TL;DR: We use convolution to make neural networks behave more like symbolic systems.

Abstract:

We argue that symmetry is an important consideration in addressing the problem
of systematicity and investigate two forms of symmetry relevant to symbolic processes.
We implement this approach in terms of convolution and show that it can
be used to achieve effective generalisation in three toy problems: rule learning,
composition and grammar learning.

Keywords: symmetry, systematicity, convolution, symbols, generalisation