Unsupervised feature recognition in single-molecule break junction data
Unsupervised feature recognition in single-molecule break junction data
复制标题
DOI：
10.1039/d0nr00467g
复制
发表时间：
2020-04-21
期刊：
影响因子：
6.7
通讯作者：
Halbritter, Andras
中科院分区：
文献类型：
--
作者：
Magyarkuti, Andras;Balogh, Nora;Halbritter, Andras
单分子断裂结测量可提供大量电导与电极分离迹线。在此类测量过程中，目标分子可能以不同的几何形状结合到电极上，并且单分子结的演变和破裂也可能遵循不同的轨迹。阐明各种典型痕迹类别是对数据进行正确物理解释的先决条件。在这里，我们利用神经网络的高效特征识别特性来自动查找相关的跟踪类别。为了消除手动标记训练数据的需要，我们应用了一种组合方法，该方法根据主成分投影的极值或一些辅助测量量自动选择训练轨迹。然后网络捕获这些特征轨迹的特征，并将其推断推广到整个数据集。使用简单的神经网络结构也可以直接洞察决策机制。我们证明，这种组合的机器学习方法可以有效地无监督地识别低温和室温金-4,4'联吡啶-金单分子断裂连接数据中不明显但高度相关的痕量类别。
Single-molecule break junction measurements deliver a huge number of conductance vs. electrode separation traces. During such measurements, the target molecules may bind to the electrodes in different geometries, and the evolution and rupture of the single-molecule junction may also follow distinct trajectories. The unraveling of the various typical trace classes is a prerequisite to the proper physical interpretation of the data. Here we exploit the efficient feature recognition properties of neural networks to automatically find the relevant trace classes. To eliminate the need for manually labeled training data we apply a combined method, which automatically selects training traces according to the extreme values of principal component projections or some auxiliary measured quantities. Then the network captures the features of these characteristic traces and generalizes its inference to the entire dataset. The use of a simple neural network structure also enables a direct insight into the decision-making mechanism. We demonstrate that this combined machine learning method is efficient in the unsupervised recognition of unobvious, but highly relevant trace classes within low and room temperature gold-4,4 ' bipyridine-gold single-molecule break junction data.