Energy landscapes for machine learning
Energy landscapes for machine learning
复制标题
DOI：
10.1039/c7cp01108c
复制
发表时间：
2017-05-28
影响因子：
3.3
通讯作者：
Wales, David J.
中科院分区：
文献类型：
--
作者：
Ballard, Andrew J.;Das, Ritankar;Wales, David J.
机器学习技术正越来越多地被用作物理科学中灵活的非线性拟合和预测工具。表现为局部极小值的多个解的拟合函数可以根据相应的机器学习环境进行分析。探索和可视化分子势能景观的方法可以应用于这些机器学习景观，以获得对训练所涉及的解空间和相应预测的性质的新见解。具体地说，我们可以定义类似于分子结构、热力学和动力学的量，并将这些新特性与潜在景观的结构联系起来。这一视角旨在用最近应用中的例子来描述这些类比，并为新的跨学科研究提供途径。
Machine learning techniques are being increasingly used as flexible non-linear fitting and prediction tools in the physical sciences. Fitting functions that exhibit multiple solutions as local minima can be analysed in terms of the corresponding machine learning landscape. Methods to explore and visualise molecular potential energy landscapes can be applied to these machine learning landscapes to gain new insight into the solution space involved in training and the nature of the corresponding predictions. In particular, we can define quantities analogous to molecular structure, thermodynamics, and kinetics, and relate these emergent properties to the structure of the underlying landscape. This Perspective aims to describe these analogies with examples from recent applications, and suggest avenues for new interdisciplinary research.