Towards Regulated Deep Learning

TL;DR

This paper proposes a novel approach called Regulated Deep Learning (RDL) that uses agent-based training and a specialized neural network model called Institutional Neural Network (INN) to address ethical, legal, and security concerns in AI.

Contribution

It introduces the concept of Artificial Teaching and demonstrates a proof-of-concept implementation of RDL using the $I^*$ language for regulating neural networks.

Findings

Demonstrated a proof-of-concept of RDL implementation.

Showed how $I^*$ can be used to regulate neural network interactions.

Highlighted the importance of regulation in AI development.

Abstract

Regulation of Multi-Agent Systems (MAS) and Declarative Electronic Institutions (DEIs) was a multidisciplinary research topic of the past decade involving (Physical and Software) Agents and Law since the beginning, but recently evolved towards News-claimed Robot Lawyer since 2016. One of these first proposals of restricting the behaviour of Software Agents was Electronic Institutions. However, with the recent reformulation of Artificial Neural Networks (ANNs) as Deep Learning (DL), Security, Privacy,Ethical and Legal issues regarding the use of DL has raised concerns in the Artificial Intelligence (AI) Community. Now that the Regulation of MAS is almost correctly addressed, we propose the Regulation of Artificial Neural Networks as Agent-based Training of a special type of regulated Artificial Neural Network that we call Institutional Neural Network (INN).The main purpose of this paper is to bring attention to Artificial Teaching (AT) and to give a tentative answer showing a proof-of-concept implementation of Regulated Deep Learning (RDL). This paper introduces the former concept and provide $I^*$, a language previously used to model declaratively and extend Electronic Institutions, as a means to regulate the execution of Artificial Neural Networks and their interactions with Artificial Teachers (ATs)