Year: 2023
Type: preprint
Abstract: Explainability has become a valuable tool in the last few years, helping humans better understand AI-guided decisions. However, the classic explainability tools are sometimes quite limited when considering high-dimensional inputs and neural network classifiers. We present a new explainability method using theoretically proven high-dimensional properties in neural network classifiers. We present two usages of it: 1) On the classical sentiment analysis task for the IMDB reviews dataset, and 2) our Malware-Detection task for our PowerShell scripts dataset.
Source: arXiv (Cornell University)
Authors: Melamed, Odelia, Caruana, Rich
Institutions: Microsoft (Israel), Microsoft (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4388963696