Chemist versus Machine: Traditional Knowledge versus Machine Learning Techniques

George, Janine; Hautier, Geoffroy

doi:10.1016/j.trechm.2020.10.007

Cited by 57 publications

(47 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, for domains with small datasets, limited features, and a strong need for higher-level inference rather than a surrogate model, ML should not necessarily be the default approach. A more traditional approach may be faster due to the error in the ML models associated with sample size, and heuristics can play a role even with larger datasets [48].…”

Section: Keep Sight Of the Goalmentioning

confidence: 99%

Reflections on the future of machine learning for materials research

Fujinuma¹,

DeCost²,

Hattrick‐Simpers³

et al. 2021

Preprint

View full text Add to dashboard Cite

Applied machine learning (ML) has rapidly spread throughout the physical sciences; in fact, ML-based data analysis and experimental decision-making has become commonplace. We suggest a shift in the conversation from proving that ML can be used to evaluating how to equitably and effectively implement ML for science. We advocate a shift from a "more data, more compute" mentality to a model-oriented approach that prioritizes using machine learning to support the ecosystem of computational models and experimental measurements. We also recommend an open conversation about dataset bias to stabilize productive research through careful model interrogation and deliberate exploitation of known biases. Further, we encourage the community to develop ML methods that connect experiments with theoretical models to increase scientific understanding rather than incrementally optimizing materials. Further, we encourage the community to develop machine learning methods that seek to connect experiments with theoretical models to increase scientific understanding rather than simply use them optimize materials. Moreover we envision a future of radical materials innovations enabled by computational creativity tools combined with online visualization and analysis tools that support active outside-the-box thinking inside the scientific knowledge feedback loop. Finally, as a community we must acknowledge ethical issues that can arise from blindly following machine learning predictions and the issues of social equity that will arise if data, code, and computational resources are not readily available to all.

show abstract

Section: Keep Sight Of the Goalmentioning

confidence: 99%

Reflections on the future of machine learning for materials research

Fujinuma¹,

DeCost²,

Hattrick‐Simpers³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…While quantum mechanics based computational materials design efforts had been undertaken as early as the nineties [81][82][83][84] with important progress made in the eighties [85,86], the first principles based computational high-throughput design has by now become an important success story [87] First attempts to employ machine learning and quantum predictions to discover new ternary materials data bases date back to seminal work by Hautier and Ceder in 2010. [88,89].…”

Section: Navigating Ccs From First Principlesmentioning

confidence: 99%

Ab initio machine learning in chemical compound space

Huang¹,

Lilienfeld²

2020

Preprint

View full text Add to dashboard Cite

Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal. The first principles based virtual exploration of this space, e.g. for designing and discovering novel molecules and materials which exhibit desirable properties, is therefore prohibitive for all but the smallest sub-sets and simplest properties, and typically requires substantial allocations on modern high-performance computing hardware. We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures inspired by quantum mechanics. Such Quantum mechanics based Machine Learning (QML) approaches combine the numerical efficiency of statistical surrogate models with an ab initio approach towards the simulation of matter which rigorously reflects the underlying physics in order to reach universality and transferability across CCS. While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the power of a physics based understanding of chemical trends and relationships.

show abstract

“… 91 First attempts to employ machine learning and quantum predictions to discover new ternary materials databases date back to seminal work by Hautier and Ceder in 2010. 92 , 93 …”

Section: Introductionmentioning

confidence: 99%

Ab Initio Machine Learning in Chemical Compound Space

2021

View full text Add to dashboard Cite

Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal. The first-principles based virtual sampling of this space, for example, in search of novel molecules or materials which exhibit desirable properties, is therefore prohibitive for all but the smallest subsets and simplest properties. We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures inspired by quantum mechanics. Such Quantum mechanics based Machine Learning (QML) approaches combine the numerical efficiency of statistical surrogate models with an ab initio view on matter. They rigorously reflect the underlying physics in order to reach universality and transferability across CCS. While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the predictive power of quantum mechanics.

show abstract

Chemist versus Machine: Traditional Knowledge versus Machine Learning Techniques

Cited by 57 publications

References 51 publications

Reflections on the future of machine learning for materials research

Reflections on the future of machine learning for materials research

Ab initio machine learning in chemical compound space

Ab Initio Machine Learning in Chemical Compound Space

Contact Info

Product

Resources

About