18512438. AUTOMLX COUNTERFACTUAL EXPLAINER (ACE) simplified abstract (Oracle International Corporation)
Contents
AUTOMLX COUNTERFACTUAL EXPLAINER (ACE)
Organization Name
Oracle International Corporation
Inventor(s)
Zahra Zohrevand of Vancouver (CA)
Ehsan Soltan Aghai of Vancouver (CA)
Yasha Pushak of Vancouver (CA)
Hesam Fathi Moghadam of Sunnyvale CA (US)
Sungpack Hong of Palo Alto CA (US)
Hassan Chafi of San Mateo CA (US)
AUTOMLX COUNTERFACTUAL EXPLAINER (ACE) - A simplified explanation of the abstract
This abstract first appeared for US patent application 18512438 titled 'AUTOMLX COUNTERFACTUAL EXPLAINER (ACE)
- Simplified Explanation:**
The patent application describes a method for generating counterfactual explanations for instances that do not have the expected class based on a reference corpus.
- Key Features and Innovation:**
- Reference corpus with multiple reference points and respective classes
- Selection of starting points based on expected class and subject point
- Generation of discrete interpolated points with expected class
- Generation of continuous interpolated points with expected class
- Direct generation of counterfactual explanations based on continuous interpolated points
- Potential Applications:**
This technology can be applied in various fields such as machine learning, artificial intelligence, data analysis, and decision-making systems.
- Problems Solved:**
This technology addresses the need for generating counterfactual explanations for instances that do not have the expected class in a more efficient and effective manner.
- Benefits:**
- Improved interpretability of machine learning models
- Enhanced decision-making processes
- Better understanding of why certain instances do not have the expected class
- Commercial Applications:**
The technology can be used in industries such as finance, healthcare, e-commerce, and cybersecurity to improve model transparency and decision-making processes.
- Prior Art:**
Researchers can explore prior work in the fields of explainable AI, counterfactual explanations, and machine learning interpretability to understand the existing knowledge in this area.
- Frequently Updated Research:**
Stay updated on advancements in explainable AI, machine learning interpretability, and decision-making systems to enhance the application of this technology.
- Questions about Counterfactual Explanation Technology:**
1. How does this technology contribute to improving the transparency of machine learning models? 2. What are the potential implications of using counterfactual explanations in decision-making processes?
Original Abstract Submitted
A computer stores a reference corpus that consists of many reference points that each has a respective class. Later, an expected class and a subject point (i.e. instance to explain) that does not have the expected class are received. Multiple reference points that have the expected class are selected as starting points. Based on the subject point and the starting points, multiple discrete interpolated points are generated that have the expected class. Based on the subject point and the discrete interpolated points, multiple continuous interpolated points are generated that have the expected class. A counterfactual explanation of why the subject point does not have the expected class is directly generated based on continuous interpolated point(s) and, thus, indirectly generated based on the discrete interpolated points. For acceleration, neither way of interpolation (i.e. counterfactual generation) is iterative. Generated interpolated points can be reused to amortize resources consumed while generating counterfactuals.
