Responsible AI tutorials | Responsible AI Toolkit

Responsible AI with TensorFlow tutorials

TensorFlow provides a variety of tools that you can apply in your workflow to develop machine learning models more responsibly. Review tutorials here to get started with tools for model fairness evaluation and remediation.

Fairness Evaluation

Introduction to Fairness Indicators

An introduction to Fairness Indicators running in a Google Colab notebook. Click the Run in Google Colab button to try it yourself.

Fairness Indicators with TF Hub Text Embeddings

Apply Fairness Indicators to evaluate commonly used fairness metrics in TF Hub Text Embedding models using the Civil Comments Dataset.

Fairness Indicators Lineage Case Study

Apply Fairness Indicators to examine fairness concerns in the COMPAS Dataset.

Remediation and Privacy

Use MinDiff with Keras

Try MinDiff, a model remediation technique that can improve model performance across commonly used fairness metrics.

Generate model cards with TFX

Use the Model Card Toolkit with TFX to generate Model Cards.

Generate privacy reports

Assess your model's privacy using the TF Privacy Report.

Videos and blog

Learn more about Responsible AI with TensorFlow on the TensorFlow blog and on YouTube!