Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values.
Yejin BangTiezheng YuAndrea MadottoZhaojiang LinMona T. DiabPascale FungPublished in: CoRR (2022)
Keyphrases
- attribute values
- ensemble learning
- training set
- support vector
- parameter values
- naive bayes
- artificial intelligence
- human interaction
- supervised classification
- human behavior
- human subjects
- training data
- decision trees
- machine learning algorithms
- multi class
- linear classifiers
- classification systems
- feature values
- bayesian classifier
- multiple classifiers
- human experts
- feature set
- classification models
- face recognition
- classification rate
- machine learning