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.
翻译:典型的高维数据建模的深层次学习方法往往导致复杂的模型,这些模型不易揭示对数据的新理解。深层学习领域的研究正在非常积极地探索新的方法来解释深神经网络并降低其复杂性。这里描述了一种方法,从线性模型开始,只有在得到数据支持的情况下,才逐步增加复杂性。一种应用方法显示,通过培训将全球温度和降水量映射到多年的模型来调查与气候变化有关的模式。