Introducing RISK

TL;DR

RISK is a system designed to enhance AI transparency by enabling real-time internal simulation of knowledge, allowing better understanding and decision-making explanations for non-expert users.

Contribution

This paper introduces the initial development of RISK, a system for rapid internal simulation to improve transparency in deep learning AI systems.

Findings

Conceptual framework for RISK introduced

Potential for improved AI transparency demonstrated

Foundation for real-time simulation in AI systems laid

Abstract

This extended abstract introduces the initial steps taken to develop a system for Rapid Internal Simulation of Knowledge (RISK). RISK aims to enable more transparency in artificial intelligence systems, especially those created by deep learning networks by allowing real-time simulation of what the system knows. By looking at hypothetical situations based on these simulations a system may make more informed decisions, and produce them for non-expert observers to understand the reasoning behind a given action.