Trustworthiness of t-Distributed Stochastic Neighbour Embedding

Machine learning based feature engineering for thermoelectric materials by design

“…A non-linear dimensionality reduction technique called t-distributed Stochastic Neighbour Embedding (t-SNE) 52 was employed to investigate the similarity in the properties of the five materials in comparison with the 8059 materials (all crystal structures) from the training set (Fig. 5F).…”

“…44 Specically, Zhou et al achieved a room temperature power factor value of 120 mW cm −1 K −2 for p-type NbFeSb, which decreased to ∼80 mW cm −1 K −2 at 600 K. Other top performing predicted materials with diverse chemistries were also studied, and the results can be found in ESI Section 12. † A non-linear dimensionality reduction technique called tdistributed Stochastic Neighbour Embedding (t-SNE) 52 was employed to investigate the similarity in the properties of the ve materials in comparison with the 8059 materials (all crystal structures) from the training set (Fig. 5F).…”