人工智能
计算机科学
机器学习
学习迁移
深度学习
核(代数)
域适应
领域(数学分析)
任务(项目管理)
高斯过程
核方法
简单(哲学)
高斯分布
支持向量机
数学
工程类
数学分析
哲学
物理
组合数学
系统工程
认识论
分类器(UML)
量子力学
作者
Massimiliano Patacchiola,Jack Turner,Elliot J. Crowley,Amos Storkey
出处
期刊:Cornell University - arXiv
日期:2019-10-11
被引量:17
摘要
Humans tackle new problems by making inferences that go far beyond the information available, reusing what they have previously learned, and weighing different alternatives in the face of uncertainty. Incorporating these abilities in an artificial system is a major objective in machine learning. Towards this goal, we adapt Gaussian Processes (GPs) to tackle the problem of few-shot learning. We propose a simple, yet effective variant of deep kernel learning in which the kernel is transferred across tasks, which we call deep kernel transfer. This approach is straightforward to implement, provides uncertainty quantification, and does not require estimation of task-specific parameters. We empirically demonstrate that the proposed method outperforms several state-of-the-art algorithms in few-shot regression, classification, and cross-domain adaptation.
科研通智能强力驱动
Strongly Powered by AbleSci AI