arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.06351cs.LG
收藏

可解释的气候变化模拟与渐进级联网络

Interpretable Climate Change Modeling With Progressive Cascade Networks

Colorado State University(科罗拉多州立大学)

Charles Anderson, Jason Stock, David Anderson

摘要:

典型的深度学习方法对高维数据进行建模,通常会产生复杂的模型,这些模型不容易揭示对数据的新理解。深度学习领域的研究正在积极寻求新的方法来解释深度神经网络并降低其复杂性。这里描述了一种方法,它从线性模型开始,只在数据支持的情况下逐步增加复杂性。一个应用程序中,全球温度和降水映射到年的模型进行训练,以调查与气候变化相关的模式。

英文摘要:

Typical deep learning approaches to modeling high-dimensional data often result in complex models that do not easily reveal a new understanding of the data. Research in the deep learning field is very actively pursuing new methods to interpret deep neural networks and to reduce their complexity. An approach is described here that starts with linear models and incrementally adds complexity only as supported by the data. An application is shown in which models that map global temperature and precipitation to years are trained to investigate patterns associated with changes in climate.

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。

↑