{"id":"W2921423946","doi":"10.1109/ijcnn.2019.8852446","title":"Transfer Learning Using Ensemble Neural Networks for Organic Solar Cell Screening","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"National Institute of Standards and Technology; U.S. Department of Energy; National Science Foundation","keywords":"Leverage (statistics); Organic solar cell; Artificial neural network; Artificial intelligence; Computer science; Deep learning; Transfer of learning; Molecular orbital; Machine learning; ENCODE; Photovoltaic system; Molecule; Chemistry; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002578925,0.0006840767,0.0009067132,0.0001730856,0.0005800201,0.001034104,0.001417388,0.0005896385,0.002765952],"category_scores_gemma":[0.0002068884,0.0006400712,0.0002971991,0.0001904159,0.0001314036,0.0004258328,0.001111778,0.001217474,0.0001264663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001090674,"about_ca_system_score_gemma":0.0001961598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003269558,"about_ca_topic_score_gemma":0.00001656026,"domain_scores_codex":[0.9952673,0.0005374572,0.0008231779,0.001562878,0.000599915,0.001209257],"domain_scores_gemma":[0.9979684,0.0004043064,0.0003424642,0.0008659872,0.0002261202,0.0001926722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000380126,0.00001325815,0.0002468747,0.0002059782,0.000004274033,0.000002238316,0.0001101407,0.550738,0.4484142,0.00002009902,0.00004068336,0.0001662927],"study_design_scores_gemma":[0.0004289685,0.0001076362,0.00005298119,0.0001173173,0.0000734477,0.00001339965,0.00007683197,0.8450651,0.1528999,0.00008756908,0.0003785649,0.0006982656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4619234,0.0001028847,0.5342458,0.00006111569,0.002340827,0.0006945327,0.00001119938,0.0002989101,0.0003213569],"genre_scores_gemma":[0.9036139,0.00001272808,0.09336936,0.0002997999,0.0006810554,0.00004353534,0.00005798688,0.0001625594,0.001759106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4416905,"threshold_uncertainty_score":0.9996051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02725840126535848,"score_gpt":0.2703931712904081,"score_spread":0.2431347700250497,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}