Learning programs is better than learning dynamics: A programmable neural network hierarchical architecture in a multi-task scenario

13Citations
Citations of this article
24Readers
Mendeley users who have this article in their library.
Get full text
This PDF is freely available from an open access repository. It may not have been peer-reviewed.

Abstract

Distributed and hierarchical models of control are nowadays popular in computational modeling and robotics. In the artificial neural network literature, complex behaviors can be produced by composing elementary building blocks or motor primitives, possibly organized in a layered structure. However, it is still unknown how the brain learns and encodes multiple motor primitives, and how it rapidly reassembles, sequences and switches them by exerting cognitive control. In this paper we advance a novel proposal, a hierarchical programmable neural network architecture, based on the notion of programmability and an interpreter-programmer computational scheme. In this approach, complex (and novel) behaviors can be acquired by embedding multiple modules (motor primitives) in a single, multi-purpose neural network. This is supported by recent theories of brain functioning in which skilled behaviors can be generated by combining functional different primitives embedded in “reusable” areas of “recycled” neurons. Such neuronal substrate supports flexible cognitive control, too. Modules are seen as interpreters of behaviors having controlling input parameters, or programs that encode structures of networks to be interpreted. Flexible cognitive control can be exerted by a programmer module feeding the interpreters with appropriate input parameters, without modifying connectivity. Our results in a multiple T -maze robotic scenario show how this computational framework provides a robust, scalable and flexible scheme that can be iterated at different hierarchical layers permitting to learn, encode and control multiple qualitatively different behaviors.

Cite

CITATION STYLE

APA

Donnarumma, F., Prevete, R., de Giorgio, A., Montone, G., & Pezzulo, G. (2016). Learning programs is better than learning dynamics: A programmable neural network hierarchical architecture in a multi-task scenario. Adaptive Behavior, 24(1), 27–51. https://doi.org/10.1177/1059712315609412

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free