Related papers: Unsupervised feature recognition in single molecul…
Improved understanding of charge-transport in single molecules is essential for harnessing the potential of molecules e.g. as circuit components at the ultimate size limit. However, interpretation and analysis of the large, stochastic…
Datasets from single-molecule experiments often reflect a large variety of molecular behaviour. The exploration of such datasets can be challenging, especially if knowledge about the data is limited and a priori assumptions about expected…
We explore the merits of neural network boosted, principal-component-projection-based, unsupervised data classification in single-molecule break junction measurements, demonstrating that this method identifies highly relevant trace classes…
A simple and fast analysis method to sort large data sets into groups with shared distinguishing characteristics is described, and applied to single molecular break junction conductance versus electrode displacement data. The method, based…
Most single-molecule transport experiments produce large and stochastic datasets containing a wide range of behaviors, presenting both a challenge to their analysis, but also an opportunity for discovering new physical insights. Recently,…
Structural breaks occur in timeseries data across a broad range of fields, from economics to nanosciences. For measurements of single-molecule break junctions, structural breaks in conductance versus displacement data occur when the…
Few-shot learning is a promising approach to molecular property prediction as supervised data is often very limited. However, many important molecular properties depend on complex molecular characteristics -- such as the various 3D…
We present an original method to estimate the conductivity of a single molecule anchored to nanometric-sized metallic electrodes, using a Mechanically Controlled Break Junction (MCBJ) operated at room temperature in liquid. We record the…
At the extreme energies of the Large Hadron Collider, massive particles can be produced at such high velocities that their hadronic decays are collimated and the resulting jets overlap. Deducing whether the substructure of an observed jet…
Accurately predicting molecular properties is a challenging but essential task in drug discovery. Recently, many mono-modal deep learning methods have been successfully applied to molecular property prediction. However, the inherent…
We propose an objective and robust method to extract the electrical conductance of single molecules connected to metal electrodes from a set of measured conductance data. Our method roots in the physics of tunneling and is tested on…
This article proposes a novel unsupervised learning framework for detecting the number of tunnel junctions in subterranean environments based on acquired 2D point clouds. The implementation of the framework provides valuable information for…
Graph neural networks (GNNs) demonstrate great performance in compound property and activity prediction due to their capability to efficiently learn complex molecular graph structures. However, two main limitations persist including…
We propose a construction for joint feature learning and clustering of multichannel extracellular electrophysiological data across multiple recording periods for action potential detection and discrimination ("spike sorting"). Our…
Feature extraction - the ability to identify relevant properties of data - is a key factor underlying the success of deep learning. Yet, it has proved difficult to elucidate its nature within existing predictive theories, to the extent that…
Unsupervised machine learning methods can be of great help in many traditional engineering disciplines, where huge amount of labeled data is not readily available or is extremely difficult or costly to generate. Two specific examples…
Electronic transport properties for single-molecule junctions have been widely measured by several techniques, including mechanically controllable break junctions, electromigration break junctions or by means of scanning tunneling…
Unsupervised learning methods for feature extraction are becoming more and more popular. We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to…
We report a method using scanning tunnelling microscope single molecular break junction to simultaneously measure and correlate the single-molecule thermopower and electrical conductance. In contrast to previously reported approaches, it…
Data classification techniques partition the data or feature space into smaller sub-spaces, each corresponding to a specific class. To classify into subspaces, physical features e.g., distance and distributions are utilized. This approach…