Book Image

Hands-On Explainable AI (XAI) with Python

By : Denis Rothman
Book Image

Hands-On Explainable AI (XAI) with Python

By: Denis Rothman

Overview of this book

Effectively translating AI insights to business stakeholders requires careful planning, design, and visualization choices. Describing the problem, the model, and the relationships among variables and their findings are often subtle, surprising, and technically complex. Hands-On Explainable AI (XAI) with Python will see you work with specific hands-on machine learning Python projects that are strategically arranged to enhance your grasp on AI results analysis. You will be building models, interpreting results with visualizations, and integrating XAI reporting tools and different applications. You will build XAI solutions in Python, TensorFlow 2, Google Cloud’s XAI platform, Google Colaboratory, and other frameworks to open up the black box of machine learning models. The book will introduce you to several open-source XAI tools for Python that can be used throughout the machine learning project life cycle. You will learn how to explore machine learning model results, review key influencing variables and variable relationships, detect and handle bias and ethics issues, and integrate predictions using Python along with supporting the visualization of machine learning models into user explainable interfaces. By the end of this AI book, you will possess an in-depth understanding of the core concepts of XAI.
Table of Contents (16 chapters)
14
Other Books You May Enjoy
15
Index

Summary

In this chapter, we built a Python client that can interact with Google Dialogflow. Our XAI chatbot can manage alert functions in the output of a machine learning algorithm.

Before implementing our chatbot, the trained machine learning algorithm would produce outputs. The user would have to wait until the ML program was finished and then activate an interactive interface.

An XAI interface, though interesting, might come too late in a decision-making process. Hundreds of automatic decisions may have been made before the user could intervene. Even if the XAI interface provides excellent explanations, bad decisions may have been made. These bad decisions must thus be analyzed, the parameters modified, and the program run again. If the errors were not damaging, then the problem can be solved with some additional configuration. But if the errors were critical, then an XAI interaction before the machine learning program ends is very productive.

Our XAI chatbot addressed...