arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.07586cs.AIcs.LGcs.LO
收藏

有限数据机器学习理论

Theory of Machine Learning with Limited Data

MetaPattern(元模式)

Marina Sapir

摘要:

机器学习的应用可以理解为通过解释累积的观察、训练集来获得新的知识以供实际使用。皮尔士用“溯因”一词来表示这种推论。在这里,我将实值假设的溯因概念形式化,并展示了14个最受欢迎的教科书ML学习者(我测试的每个学习者),包括分类,回归和聚类,实现了这种溯因推理的概念。该方法是作为统计学习理论的替代方案提出的,统计学习理论需要无限增加训练集的不切实际的假设来证明其合理性。

英文摘要:

Application of machine learning may be understood as deriving new knowledge for practical use through explaining accumulated observations, training set. Peirce used the term abduction for this kind of inference. Here I formalize the concept of abduction for real valued hypotheses, and show that 14 of the most popular textbook ML learners (every learner I tested), covering classification, regression and clustering, implement this concept of abduction inference. The approach is proposed as an alternative to statistical learning theory, which requires an impractical assumption of indefinitely increasing training set for its justification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑