Summary of Robustness Of Explainable Artificial Intelligence in Industrial Process Modelling, by Benedikt Kantz et al.
Robustness of Explainable Artificial Intelligence in Industrial Process Modelling
by Benedikt Kantz, Clemens Staudinger, Christoph Feilmayr, Johannes Wachlmayr, Alexander Haberl, Stefan Schuster, Franz Pernkopf
First submitted to arxiv on: 12 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper evaluates current Explainable Artificial Intelligence (XAI) methods by scoring them based on ground truth simulations and sensitivity analysis. The authors used an Electric Arc Furnace (EAF) model as a test case, applying XAI methods such as SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), Averaged Local Effects (ALE), and Smooth Gradients (SG). The evaluation showed that the capability of machine learning models to capture the process accurately is coupled with the correctness of the explainability of the underlying data-generating process. The results highlight differences between XAI methods in correctly predicting the true sensitivity of the modeled industrial process. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how AI can be more transparent and explainable. Scientists tested different AI methods to see which ones do a good job explaining how they make predictions. They used a real-life example, like a big metal factory furnace, to test these methods. The results show that some AI methods are better than others at correctly explaining what’s going on in the data. This is important because we need AI to be able to tell us why it made certain decisions. |
Keywords
* Artificial intelligence * Machine learning
