{"id":"W4309310085","doi":"10.3390/rs14225774","title":"Quantum Based Pseudo-Labelling for Hyperspectral Imagery: A Simple and Efficient Semi-Supervised Learning Method for Machine Learning Classifiers","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs; Sapienza Università di Roma; Innovation Saskatchewan","keywords":"Support vector machine; Hyperspectral imaging; Quantum machine learning; Computer science; Decision tree; Artificial intelligence; Random forest; Machine learning; Quantum; Boosting (machine learning); Classifier (UML); Quantum computer; Pattern recognition (psychology); Algorithm; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001848998,0.0003090119,0.0004148938,0.0002653241,0.002182035,0.0002687972,0.0003255546,0.00006394967,0.00000259422],"category_scores_gemma":[0.0003402868,0.0003185123,0.0002248583,0.0005046321,0.00004464715,0.00006336021,0.0003158696,0.0007740499,5.347335e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001252685,"about_ca_system_score_gemma":0.0001119958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009946308,"about_ca_topic_score_gemma":0.0000024492,"domain_scores_codex":[0.9971876,0.0004627877,0.0003526427,0.0008814749,0.0003504238,0.0007650828],"domain_scores_gemma":[0.9976668,0.00154809,0.0002077355,0.0003133925,0.0001067082,0.0001572288],"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":[0.00004900519,0.00001686708,0.000005220612,0.00005864592,0.00002382016,0.00001681096,0.001232715,0.7394888,0.02999883,0.0003128766,0.00002300009,0.2287734],"study_design_scores_gemma":[0.001242654,0.0003916742,0.000004638909,0.00004249985,0.00003137972,0.0001359583,0.0003873418,0.9901549,0.00172716,0.001353567,0.004123695,0.0004045932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1664349,0.0002468533,0.8310488,0.001173185,0.0002841261,0.0004422243,0.000007744291,0.0003422679,0.00001985882],"genre_scores_gemma":[0.3022269,0.000003124192,0.6972342,0.0002907049,0.0001246092,5.346943e-7,0.00002639885,0.00005015064,0.00004345355],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2506661,"threshold_uncertainty_score":0.9999267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01717182392277426,"score_gpt":0.2635989655010669,"score_spread":0.2464271415782927,"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."}}