Conformal and Probabilistic Prediction with Applications
摘要截稿:
全文截稿: 2020-07-30
影响因子: 7.196
期刊难度:
CCF分类: B类
中科院JCR分区:
• 大类 : 计算机科学 - 1区
• 小类 : 计算机:人工智能 - 1区
• 小类 : 工程:电子与电气 - 1区
Overview
This issue will be devoted to conformal prediction, a novel machine learning technique
that complements predictions of ML algorithms with reliable measures of confidence.
The methods developed based on this framework produce well-calibrated confidence measures for individual examples without assuming anything more than that the data are generated independently from the same probability distribution (the i.i.d. model). Topic includes:
Theoretical analysis of conformal prediction, including performance guarantees
Applications of conformal prediction in various fields, including bioinformatics, drug discovery, medicine, natural language processing, robotics and information security
Novel conformity measures
Conformal anomaly detection
Venn prediction and other methods of multiprobability prediction
Conformal predictive distributions
Probabilistic prediction
On-line compression modelling
Prediction in: Machine learning, Pattern recognition, Data mining, Transfer learning