Montreal AI Ethics Institute's Response to Scotland's AI Strategy

TL;DR

The paper analyzes the Scottish Government's AI strategy, emphasizing the need for ethical guidelines, transparency, and inclusion, and proposes extending the strategy to address biometric data and the stochastic nature of deep learning.

Contribution

It provides a critical review of Scotland's AI strategy from an ethical perspective and suggests concrete extensions and considerations for responsible AI development.

Findings

Highlights the importance of ethical guidelines and transparency.

Recommends including biometric data considerations.

Stresses addressing the stochastic nature of deep learning.

Abstract

In January and February 2020, the Scottish Government released two documents for review by the public regarding their artificial intelligence (AI) strategy. The Montreal AI Ethics Institute (MAIEI) reviewed these documents and published a response on 4 June 2020. MAIEI's response examines several questions that touch on the proposed definition of AI; the people-centered nature of the strategy; considerations to ensure that everyone benefits from AI; the strategy's overarching vision; Scotland's AI ecosystem; the proposed strategic themes; and how to grow public confidence in AI by building responsible and ethical systems. In addition to examining the points above, MAIEI suggests that the strategy be extended to include considerations on biometric data and how that will be processed and used in the context of AI. It also highlights the importance of tackling head-on the inherently stochastic nature of deep learning systems and developing concrete guidelines to ensure that these systems are built responsibly and ethically, particularly as machine learning becomes more accessible. Finally, it concludes that any national AI strategy must clearly address the measurements of success in regards to the strategy's stated goals and vision to ensure that they are interpreted and applied consistently. To do this, there must be inclusion and transparency between those building the systems and those using them in their work.