An increasing concern is that rapid surge in the complexity and sophistication of AI models has evolved to such an extent that humans do not understand the complex mechanisms by which AI models make certain decisions. This understanding, referred to as “explainability” or “interpretability,” allows users to gain insight into the machine’s decision-making process. The need for trust in AI has been of importance and one way of achieving it is through creating explainable workflows throughout the AI application lifecycle. This course will give you an overview on the concept of explainability which helps in building trust in AI and how the "AI Explainability 360" open source toolkit can help you create explainable machine learning models.

Note that hands-on labs are included with this course.

IBM Customers and Sellers: If you are interested in investing in your training, please consider the following Individual or Enterprise Subscriptions:

• IBM Learning for Data and AI Individual Subscription (SUBR022G)
• IBM Learning for Data and AI Enterprise Subscription (SUBR004G)
• IBM Learning Individual Subscription with Red Hat Learning Services (SUBR023G)

The Big Picture of Trustworthy AI and AI Explainability 
• Recognize the need for Trustworthy AI 
• Describe and differentiate various factors that can build trust in AI 
• Appraise situations that require a focus on AI explainability 
• Recognize different methods of achieving explainability 

Methods for Explainable AI & Overview of AI Explainability 360 Toolkit 
• Identify different methods of achieving Explainable AI 
• Recognize the role of open-source AI Explainability 360 toolkit in supporting explainability 
• Describe various features and capabilities of the open-source AI Explainability 360 toolkit 

Hands-on with AI Explainability 
• Conduct an end-to-end explainability exercise, including model-building, evaluation, and other considerations pertaining to explainability 
• Apply explainability algorithms to create interpretable models

This course is intended primarily for Analytics Leaders, Data Science Leaders and Practicing Data Scientists, Machine Learning Engineers and AI specialists. Anyone with interest in Explainable AI and AI Trust having the prerequisite knowledge required.

In order to be successful, you should have a basic understanding of Data Science workflow, Data Preprocessing, Feature Engineering, Machine Learning Models, Hyperparameter Optimization, Evaluation measures for models, Python Helpful but not necessary. Two helpful, but not necessary, courses to consider: Reducing Unfair Bias in Machine Learning and AI FactSheets for Transparency and Governance

• The Big Picture of Trustworthy AI and AI Explainability 
• Methods for Explainable AI & Overview of AI Explainability 360 Toolkit 
• Hands-on with AI Explainability