Using test-time augmentation to investigate explainable AI: inconsistencies between method, model and human intuition

Using test-time augmentation to investigate explainable AI: inconsistencies between method, model and human intuition

Abstract Stakeholders of machine learning models desire explainable artificial intelligence (XAI) to produce human-understandable and consistent interpretations. In computational toxicity, augmentation of text-based molecular representations has been used successfully for transfer learning on downst...

Full description

Bibliographic Details
Main Authors: Peter B. R. Hartog, Fabian Krüger, Samuel Genheden, Igor V. Tetko
Format: Article
Language:English
Published: BMC 2024-04-01
Series:Journal of Cheminformatics
Subjects:
ML
XAI
Robustness
Test-time augmentation
Interpretation
Representation learning
Online Access:https://doi.org/10.1186/s13321-024-00824-1

Internet

https://doi.org/10.1186/s13321-024-00824-1

Similar Items