A modular architecture for transparent computation in Recurrent Neural Networks

TL;DR

This paper introduces a modular neural network architecture that enables transparent, real-time simulation of automata and symbolic operations without training, bridging neural dynamics and symbolic computation.

Contribution

It proposes a novel architecture based on nonlinear dynamical automata and versatile shifts, supporting transparent and localizable symbolic processing in recurrent neural networks.

Findings

Networks simulate automata in real-time

Architecture supports symbolic operations without training

Demonstrated with locomotion control and sentence parsing

Abstract

Computation is classically studied in terms of automata, formal languages and algorithms; yet, the relation between neural dynamics and symbolic representations and operations is still unclear in traditional eliminative connectionism. Therefore, we suggest a unique perspective on this central issue, to which we would like to refer as to transparent connectionism, by proposing accounts of how symbolic computation can be implemented in neural substrates. In this study we first introduce a new model of dynamics on a symbolic space, the versatile shift, showing that it supports the real-time simulation of a range of automata. We then show that the Goedelization of versatile shifts defines nonlinear dynamical automata, dynamical systems evolving on a vectorial space. Finally, we present a mapping between nonlinear dynamical automata and recurrent artificial neural networks. The mapping defines an architecture characterized by its granular modularity, where data, symbolic operations and their control are not only distinguishable in activation space, but also spatially localizable in the network itself, while maintaining a distributed encoding of symbolic representations. The resulting networks simulate automata in real-time and are programmed directly, in absence of network training. To discuss the unique characteristics of the architecture and their consequences, we present two examples: i) the design of a Central Pattern Generator from a finite-state locomotive controller, and ii) the creation of a network simulating a system of interactive automata that supports the parsing of garden-path sentences as investigated in psycholinguistics experiments.