Contrastive learning is a newer approach to finding similar and dissimilar candidate objects in a machine learning pipeline. The contrastive explanation aims to find the similarity between two features to help the prediction of a class. Typical black box models trained on different types of hyper parameters and a bunch of parameters optimized on various epochs and learning rates are very hard to interpret and even harder to reason why the model predicted ...
© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2022
P. MishraPractical Explainable AI Using Pythonhttps://doi.org/10.1007/978-1-4842-7158-2_1111. Contrastive Explanations for Machine Learning
Pradeepta Mishra1
(1)
Sobha Silicon Oasis, Bangalore, Karnataka, India
Get Practical Explainable AI Using Python: Artificial Intelligence Model Explanations Using Python-based Libraries, Extensions, and Frameworks now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
