US Patent Application 18323843. MISUSE INDEX FOR EXPLAINABLE ARTIFICIAL INTELLIGENCE IN COMPUTING ENVIRONMENTS simplified abstract
MISUSE INDEX FOR EXPLAINABLE ARTIFICIAL INTELLIGENCE IN COMPUTING ENVIRONMENTS
Organization Name
Inventor(s)
GLEN J. Anderson of Beaverton OR (US)
RAJESH Poornachandran of Portland OR (US)
KSHITIJ Doshi of Tempe AZ (US)
MISUSE INDEX FOR EXPLAINABLE ARTIFICIAL INTELLIGENCE IN COMPUTING ENVIRONMENTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18323843 titled 'MISUSE INDEX FOR EXPLAINABLE ARTIFICIAL INTELLIGENCE IN COMPUTING ENVIRONMENTS
Simplified Explanation
The patent application describes a mechanism for measuring the misuse index of explainable artificial intelligence in computing environments.
- The mechanism involves mapping training data used to train a machine learning model with its inference uses.
- Discrepancies between the training data and the inference uses are detected based on policy/parameter thresholds.
- These discrepancies are classified as misuses and a misuse index is created to list these misuses.
Original Abstract Submitted
A mechanism is described for facilitating misuse index for explainable artificial intelligence in computing environments, according to one embodiment. A method of embodiments, as described herein, includes mapping training data with inference uses in a machine learning environment, where the training data is used for training a machine learning model. The method may further include detecting, based on one or more policy/parameter thresholds, one or more discrepancies between the training data and the inference uses, classifying the one or more discrepancies as one or more misuses, and creating a misuse index listing the one or more misuses.
