.png){kind=icon}
返回
Multicriteria interpretability driven deep learning
.png){kind=icon}
OA
AI
DOI：10.1007/s10479-022-04692-6.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep Learning methods are well-known for their abilities, but their interpretability keeps them out of high-stakes situations. This difficulty is addressed by recent model-agnostic methods that provide explanations after the training process. As a result, the current guidelines' requirement for interpretability from the start is not met. As a result, such methods are only useful as a sanity check after the model has been trained. In an abstract scenario, interpretability from the start implies imposing a set of soft constraints on the model's behavior by infusing knowledge and eliminating any biases. By inserting knowledge into the objective function, we present a Multicriteria technique that allows us to control the feature effects on the model's output. To accommodate for more complex effects and local lack of information, we enhance the method by integrating particular knowledge functions. As a result, a Deep Learning training process that is both interpretable and compliant with modern legislation has been developed. Our technique develops performant yet robust models capable of overcoming biases resulting from data scarcity, according to a practical empirical example based on credit risk.
Keyword:
Artificial intelligence
Machine learning
Deep learning
Multiple objective programming
Multicriteria optimization
期刊
IF:
4.5
论文数:
8.1K
被引数:
2.1W
机构
引用论文
.png){kind=icon}
Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction
PREAI
分享收藏The JuliaConnectoR: A Functionally-Oriented Interface for Integrating Julia in RJulliaconnector: 用于在R中集成Julia的面向功能的接口OAAI
OAAI分享收藏On the macroeconomic determinants of long-term volatilities and correlations in U.S. stock and crude oil markets关于美国股票和原油市场长期波动和相关性的宏观经济决定因素
PREAI
分享收藏Validity of Current Stereotactic Body Radiation Therapy Dose Constraints for Aorta and Major Vessels
PREAI
分享收藏
IMU Preintegration on Manifold for Efficient Visual-Inertial Maximum-a-Posteriori Estimation用于有效视觉惯性最大后验估计的流形上的IMU预积分OAAI
OAAI分享收藏
查看更多内容