The exploration and application of Machine Learning tools has become an underpinning theme in various aspects of our work, including dimensionality reduction techniques (PCA, MPVC, t-SNE), Autoencoders for unsupervised classification, Support Vector Machines, and Deep Learning methods such as Convolutional Neural Networks.

References

1. Unsupervised classification of single-molecule data with autoencoders and transfer learning
   Anton Vladyka and Tim Albrecht.
   Machine Learning: Science and Technology 1, 35013 (2020)
   [Show/hide abstract]

   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 data characteristics are to be avoided. Indeed, searching for pre-defined signal characteristics is sometimes useful, but it can also lead to information loss and the introduction of expectation bias. Here, we demonstrate how Transfer Learning-enhanced dimensionality reduction can be employed to identify and quantify hidden features in single-molecule charge transport data, in an unsupervised manner. Taking advantage of open-access neural networks trained on millions of seemingly unrelated image data, our results also show how Deep Learning methodologies can readily be employed, even if the amount of problem-specific, ‘own’ data is limited.

2. Deep learning for single-molecule science
   Tim Albrecht, Gregory Slabaugh, Eduardo Alonso, and SM Masudur R. Al-Arif.
   Nanotechnology 28, 423001 (2017)
3. Unsupervised vector-based classification of single-molecule charge transport data
   Mario Lemmer, Michael S. Inkpen, Katja Kornysheva, Nicholas J. Long, and Tim Albrecht.
   Nature Communications 7, 1–10 (2016)