Summary of Causal Perception, by Jose M. Alvarez and Salvatore Ruggieri
Causal Perception
by Jose M. Alvarez, Salvatore Ruggieri
First submitted to arxiv on: 24 Jan 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
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 machine learning paper tackles the concept of perception in decision-making, where individuals interpret information differently due to their unique experiences. The authors aim to account for this phenomenon by formulating it using structural causal models (SCM). They define perception as individual experience influencing a human expert’s decision-making process. Two types of causal perception are identified: unfaithful and inconsistent, based on SCM properties. The paper highlights the importance of considering perception in fairness problems, particularly in modern decision flows involving machine learning applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Perception is when people see things differently because of their experiences. This can affect how we make decisions. Imagine two experts looking at the same information but coming to different conclusions. This happens often and can lead to unfair results. The authors want to understand this phenomenon better by using special models called structural causal models (SCM). They define perception as when a person’s experience affects their decision-making process. Two types of perception are identified: when someone is not faithful or consistent in their understanding. The paper shows that considering perception is important for making fair decisions, especially with the help of machine learning. |
Keywords
* Artificial intelligence * Machine learning
