发表机构
University of Helsinki（赫尔辛基大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文指出无监督学习是异质领域，无法定义单一目标，明确其四个核心目标为估计分布、生成新数据点、提取下游任务特征及理解数据。
AI 中文摘要
无监督学习是机器学习的主要分支之一。本文指出，与机器学习的其他分支（监督学习和强化学习）不同，无监督学习是一个相当异质的领域，可服务于多个不同目标，试图为其定义单一目标是徒劳的。作者确定了无监督学习的四个不同目标：1）估计分布；2）生成新数据点；3）为下游任务提取特征；4）理解数据。
英文摘要
Unsupervised learning is one of the main branches of machine learning. Here I argue that unlike the other branches of machine learning (supervised and reinforcement learning), unsupervised learning is a rather heterogenous field that can serve several different goals. It seems futile to try to define one single goal for unsupervised learning. I identify four different goals for unsupervised learning: 1) Estimating the distribution, 2) Generating new data points, 3) Extracting features for downstream tasks, and 4) Understanding the data.
