T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients

arXiv:2404.16495v1 Announce Type: new
Abstract: The development of machine learning applications has increased significantly in recent years, motivated by the remarkable ability of learning-powered systems to discover and generalize intricate patterns hidden in massive datasets. Modern learning models, while powerful, often exhibit a level of complexity that renders them opaque black boxes, resulting in a notable lack of transparency that hinders our ability to decipher their decision-making processes. Opacity challenges the interpretability and practical application of machine learning, especially in …

abstract applications arxiv black boxes complexity cs.lg datasets development explainability explainer framework hidden machine machine learning machine learning applications massive model-agnostic modern patterns systems them type while