Monitoring AI Models for Bias & Fairness with Segmentation скачать в хорошем качестве

Monitoring AI Models for Bias & Fairness with Segmentation

Workshop links to follow along: WhyLabs free sign-up: https://whylabs.ai/free Google Colab: https://s.whylabs.io/intro-ml-monitor whylogs github (give us a star!) https://github.com/whylabs/whylogs/ Join The AI Slack group: https://bit.ly/r2ai-slack In this workshop we’ll cover how to get started with ML monitoring for bias & fairness with segmentation and performance tracing. Deploying machine learning (ML) models is only part of the journey. Monitoring data pipelines and model performance is critical to ensure AI applications are robust and responsible. This workshop will cover: How bias & fairness can happen in machine learning How to use segmentation to understand model bias How to use performance tracing to debug ML models in production Receive a certificate for each workshop completed! We regularly host live workshops to guide you at any stage of your machine learning journey. These sessions aim to provide an understanding of ML monitoring and AI observability's essential role in MLOps while equipping you with the tools and techniques to effectively manage and monitor your models and systems. Getting Started with ML Monitoring & AI Observability Monitoring ML Models and Data in Production ML Monitoring for Bias & Fairness with Tracing Understand Models with ML Explainability & Monitoring Register for these upcoming events at: https://whylabs.ai/events What you’ll need to follow along: A modern web browser A Google account (for saving a Google Colab) Sign up free a free WhyLabs account (https://whylabs.ai/free) Who should attend: Anyone interested in AI observability, ML model monitoring, MLOps, and DataOps! This workshop is designed to be approachable for most skill levels. Familiarity with machine learning and Python will be useful, but it's not required to attend. By the end of this workshop series, you’ll be able to implement data and AI observability into your own pipelines (Kafka, Airflow, Flyte, etc) and ML applications to catch deviations and biases in data or ML model behavior. About the instructor: Sage Elliott enjoys breaking down the barrier to AI observability, talking to amazing people in the Robust & Responsible AI community, and teaching workshops on machine learning. Sage has worked in hardware and software engineering roles at various startups for over a decade. Connect with Sage on LinkedIn:   / sageelliott   About WhyLabs: WhyLabs.ai is an AI observability platform that prevents data & model performance degradation by allowing you to monitor your data and machine learning models in production. Check out our open-source ML monitoring project: https://github.com/whylabs/whylogs Do you want to connect with the team, learn about WhyLabs, or get support? Join the WhyLabs + Robust & Responsible AI community Slack: http://join.slack.whylabs.ai/