From the course: AWS Certified AI Practitioner (AIF-C01) Cert Prep

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

AWS AI bias detection tools

AWS AI bias detection tools - Amazon Web Services (AWS) Tutorial

From the course: AWS Certified AI Practitioner (AIF-C01) Cert Prep

Start my 1-month free trial Buy for my team

AWS AI bias detection tools

“

- AWS has tools for detecting bias in AI models. Let's take a look at some of those now, and we're going to start with SageMaker Clarify, and its whole purpose is to detect and mitigate bias in ML models before deployment. It allows you to detect data skew and bias during the training process so you don't have to catch it retroactively. It also gives insights into the decision-making ability of the model, and it can continuously monitor the models in production once they've been deployed for ensuring both fairness and transparency. Our next tool is SageMaker Model Monitor, and this is a another tool that can work in production to monitor those models, to detect data quality issues as well as performance degradation, so it changes over time. And so it looks at model drift, data drift, as well as feature distribution, and it can notify users when it identifies deviations from the expected behavior, as well as capturing the relevant metrics without any manual setup required. And our…

Contents