From the course: Microsoft Azure AI Essentials: Workloads and Machine Learning on Azure

Unlock this course with a free trial

Join today to access over 24,700 courses taught by industry experts.

Achieving AI transparency

Achieving AI transparency

From the course: Microsoft Azure AI Essentials: Workloads and Machine Learning on Azure

Start my 1-month free trial Buy for my team

Achieving AI transparency

“

- [Speaker] AI systems must be transparent and understandable. Key stakeholders need to be fully-informed about the system's purpose, how it operates, and its limitations. For example, when developing a machine learning model for loan approvals in a bank or admissions-decisions in an educational institution, it's essential to clearly communicate the role of AI. Stakeholders should know how the model generates outputs and the reasoning behind its decisions. Transparency can be broken down into three key areas. First, system intelligibility for decision-making. This is ensuring that AI system outputs are clear and support stakeholder needs. It also involves understanding the system's intended use, how it makes decisions, and the risks of over-reliance. It's also vital to document how stakeholders can be evaluated to ensure the properly interpret system outputs. Second area is communication to stakeholders. Decision makers need to be informed about the system's capabilities, how it…

Contents