Unsupervised feature recognition in single molecule break junction data

Abstract

Single-molecule break junction measurements deliver a huge number of conductance vs.\ electrode separation traces. Along 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 of 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, and 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 to 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.

References in corpus (10)

• Quantum properties of atomic-sized conductors
• Formation and manipulation of a metallic wire of single gold atoms
• Mechanically-Controlled Binary Conductance Switching of a Single-Molecule Junction
• Amine-Gold Linked Single-Molecule Junctions: Experiment and Theory
• Formation and Evolution of Single Molecule Junctions
• Regular atomic narrowing of Ni, Fe and V nanowires resolved by 2D correlation analysis
• Fast data sorting with modified principal component analysis to distinguish unique single molecular break junction trajectories
• Transition from tunneling to direct contact in tungsten nanojunctions
• Pulling Platinum Atomic Chains by Carbon Monoxide Molecules
• Temporal correlations and structural memory effects in break junction measurements

Cited by in corpus (4)

• Unsupervised Segmentation-Based Machine Learning as an Advanced Analysis Tool for Single Molecule Break Junction Data
• Voltage-controlled binary conductance switching in gold-4,4'-bipyridine-gold single-molecule nanowires
• Grid-Based Correlation Analysis to Identify Rare Quantum Transport Behaviors
• An experimental set up to probe the quantum transport through single atomic/molecular junction at room temperature