Introducing RISK
This addresses the problem of AI transparency for non-expert users, but it is incremental as it describes initial steps without proven results.
The paper introduces RISK, a system for Rapid Internal Simulation of Knowledge, aiming to enhance transparency in AI by enabling real-time simulation of what deep learning networks know, which could lead to more informed decisions and understandable reasoning for non-experts.
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.