Finally there are problems with additivity to models: learning new cases tends to overwrite existing expertise and predicting properties and responses outside of the original model are not usually possible.Ī counterpoint to these methods is the experiences of the past 20 years with approximate quantum mechanical methods, which now represent an essential part of computational tools for a solid atomistic understanding of a broad range of physical, chemical and biological problems for both large and challenging systems. Then issues of the explainability and explicability of the predictions also matter, particularly with some of the more powerful ML methods. Firstly, reproducibility in the training of models is a current topic of active debate receiving substantial attention and within the last year calls for more physical based approaches are beginning to appear. However, there are several issues which require careful thought in deploying these tools.
Its ability to use existing examples to rapidly make meaningful predictions in new cases offers a new way to screen wide ranges of structures and to estimate the results of highly accurate methods at much reduced cost. The field of machine learning (ML) is already making rapid and tremendous impact at the interfaces of the traditional disciplines of Chemistry, Physics, Biology and materials science.