article thumbnail

Explaining black-box models using attribute importance, PDPs, and LIME

Domino Data Lab

The interest in interpretation of machine learning has been rapidly accelerating in the last decade. This can be attributed to the popularity that machine learning algorithms, and more specifically deep learning, has been gaining in various domains. Methods for explaining Deep Learning.

Modeling 139
article thumbnail

How can CIOs protect Personal Identifiable Information (PII) for a new class of data consumers?

CIO Business Intelligence

The new class often uses advanced techniques such as deep learning, natural language processing, and computer vision to analyze and extract insights from the data. It is often used to train machine learning models and protect sensitive data in healthcare and finance. The solution is also partially risk-free.