How to show biases in ML models ?
The What-If Tool: Code-Free Probing of Machine Learning Models
The tool Lets users analyze an ML model without writing code. Given pointers to a TensorFlow model and a datase.
Allows users to visualize possible bias in machine learning models
How would changes to a datapoint affect my model’s prediction? Does it perform differently for various groups–for example, historically marginalized people? How diverse is the dataset I am testing my model on?
Last updated
Was this helpful?