From the course: MLOps Essentials: Model Deployment and Monitoring
Join today to access over 24,400 courses taught by industry experts.
Explainable AI
From the course: MLOps Essentials: Model Deployment and Monitoring
Explainable AI
- [Instructor] The ability to interpret why a model is predicting in a certain way is becoming more and more important as AI faces challenges from governments and society about its ethics. Explainable AI, or XAI for short, is a set of processes and tools that allows humans to understand model behavior by correlating the output to the input features that influenced it. This is reverse engineering the behavior of a model to explain which features impacted a specific prediction. Why do we need explainable AI? Models are becoming black boxes. As we focus more and more on deep learning models, especially for NLP and vision applications, it's not possible to understand why a model is predicting in a certain manner. As a result, questions arise about its accuracy and fairness, and whether it is performing like a human in these situations. Lack of trust in society is impacting the growth of AI and limiting its applications.…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
