Traditional machine learning is well-known for needing a large amount of training data. However, real-life data derived from experiments is not only expensive but also time-consuming to collect so there is never enough data available. How can we respond?
In this white paper we review how the Alchemite™ deep learning method uses property-property correlations, uncertainty estimates, design of experiments, and validation to overcome inevitable lack of data. Each approach is tried and tested in the real world, backed up by experimental validation of materials and drugs. Alchemite™ allows machine learning to be applied to systems with apparently impossibly small amounts of data, opening opportunities to apply the power of machine learning to systems previously inaccessible due to the lack of data.
This topic was also the focus of an Intellegens webinar – a recording is available.