The Institute for Ethical AI & Machine Learning

XAI - eXplainableAI Framework

An eXplainability framework for Machine Learning

The XAI Framework allows you to introduce explainability and perform bias evaluation in AI systems by going beyond algorithms using a tool+process approach.

The XAI Framework is fully open source, and the eXplainability Framework is currently in ALPHA stage. If you're interested to learn more, get in touch.

XAI - The eXplainable AI Framework [ALPHA]

Combining cutting edge research tools with practical industry processes to ensure machine learning systems are explainable and undesired biases are mitigated.

The XAI Framework is open source, and converts the Principles for Responsible Machine Learning into a practical tool + process approach.

What do we mean by eXplainable AI?

We see the challenge of explainability as more than just an algorithmic challenge. The XAI Framework is designed to empowers you to introduce explainability and perform bias evaluation through three steps: 1) data analysis, 2) model evaluation, and 3) production monitoring. This is visualised in the diagram below.

Check out our hands on case study where we introduce explainability and remove undesired biases in a credit risk / loan approval process using deep learning. Watch the technical video below.