Summary of Uncertainty-aware Explanations Through Probabilistic Self-explainable Neural Networks, by Jon Vadillo et al.
Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networks
by Jon Vadillo, Roberto Santana, Jose A. Lozano, Marta Kwiatkowska
First submitted to arxiv on: 20 Mar 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 The paper proposes a probabilistic reformulation of Prototype-Based Self-Explainable Neural Networks (PSENNs), called Prob-PSENN, which replaces point estimates for prototypes with probability distributions over their values. This allows for capturing explanatory uncertainty and detecting uninformed or uncertain predictions. The authors demonstrate that Prob-PSENNs provide more meaningful and robust explanations than non-probabilistic counterparts while maintaining competitive predictive performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making Deep Neural Networks (DNNs) more transparent so they can be trusted in important situations. Right now, DNNs don’t clearly show how they make their predictions, which makes them unreliable. The researchers introduce a new approach called Prob-PSENN that uses probability to explain its decisions. This helps identify when the model is unsure or making uninformed predictions. They test this method and find it gives better explanations while still being accurate in predicting outcomes. |
Keywords
* Artificial intelligence * Probability
