arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14290cs.LGstat.ML
收藏

使用特权信息的动态元学习

Meta-learning using privileged information for dynamics

University of Cambridge(剑桥大学)

Ben Day, Alexander Norcliffe, Jacob Moss, Pietro Liò

摘要:

神经ODE过程使用潜变量模型来处理动态的元学习问题,该模型允许灵活地聚合上下文信息。这种灵活性继承自神经过程框架,并允许模型将任意大小的上下文观察集合聚合到固定长度的表示中。在物理科学中,除了对系统的原始观察之外,我们还经常可以获得结构化知识,例如守恒量的值或对已理解组件的描述。利用聚合灵活性,我们扩展了神经ODE过程模型,以使用“使用特权信息学习”设置中的额外信息,并且我们通过实验验证了我们的扩展,这些实验表明模拟动力学任务的准确性和校准得到了提高。

英文摘要:

Neural ODE Processes approach the problem of meta-learning for dynamics using a latent variable model, which permits a flexible aggregation of contextual information. This flexibility is inherited from the Neural Process framework and allows the model to aggregate sets of context observations of arbitrary size into a fixed-length representation. In the physical sciences, we often have access to structured knowledge in addition to raw observations of a system, such as the value of a conserved quantity or a description of an understood component. Taking advantage of the aggregation flexibility, we extend the Neural ODE Process model to use additional information within the Learning Using Privileged Information setting, and we validate our extension with experiments showing improved accuracy and calibration on simulated dynamics tasks.

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。

↑