A modular architecture for transparent computation in Recurrent Neural Networks

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.

READ FULL TEXT
research
11/04/2015

Turing Computation with Recurrent Artificial Neural Networks

We improve the results by Siegelmann & Sontag (1995) by providing a nove...
research
02/04/2023

Invariants for neural automata

Computational modeling of neurodynamical systems often deploys neural ne...
research
12/15/2017

Ergodicity of some classes of cellular automata subject to noise

Cellular automata (CA) are dynamical systems on symbolic configurations ...
research
01/27/2023

Hydrodynamic and symbolic models of hypercomputation

Dynamical systems and physical models defined on idealized continuous ph...
research
07/07/2020

Resonator networks for factoring distributed representations of data structures

The ability to encode and manipulate data structures with distributed ne...
research
06/04/2019

Sequential Neural Networks as Automata

This work attempts to explain the types of computation that neural netwo...
research
10/19/2022

Transformers Learn Shortcuts to Automata

Algorithmic reasoning requires capabilities which are most naturally und...

Please sign up or login with your details

Forgot password? Click here to reset