CROW (2015) Polymer Properties Database [Internet]. Available at:http://www.polymerdatabase.com(Accessed 10 October 2021). The Center for Hierarchical Materials Design (CHiMaD) (2015). Polymer Property Predictor and Database [Internet]. Available at:https://pppdb.uchicago.edu(Accessed 10 Octo...
01 March 2016 A polymer dataset for accelerated property prediction and design Tran Doan Huan1, Arun Mannodi-Kanakkithodi1, Chiho Kim1, Vinit Sharma1,†, Ghanshyam Pilania2 & Rampi Ramprasad1 Emerging computation- and data-driven approaches are particularly useful for rationally designing materi...
information relevant to a specific sub-domain can be obtained through heuristic rules and regular expressions which would be unsupervised. 3. Converting polymer names to a structure (typically a SMILES string14) is also a bottleneck to training property predictor models as this must be done ...
To build a predictor that reduces random errors, we use the robustness of neural networks against random noises in the training data, previously demonstrated in images20and graphs21. We assume that there exists a true target property (e.g., conductivity) that is uniquely determined by the struc...
where D denotes the composite desirability function; d1, d2 and d3 are individual desirability functions corresponding to the responses; x is the vector of the designed variables (coded values); tensile strength(x), modulus of elasticity (x), and impact strength(x) are the predictor of the...
It can be seen that the ET model is the least accurate predictor of the three base learners, with 𝑅2R2 values on the train and test sets of 0.951 and 0.894, respectively. In contrast, the 𝑅2R2 value for the EML model on the train and test sets, respectively, is promoted to ...
A GP model, before conditioning on data, is unanimously specified by its mean and covariance functions (e.g., the kernel) [39]. Covariance employs the assumptions about the function to learn and it is the main ingredient to guide the GP predictor. Popular kernels incorporated are the squared...