{"id":"W2604587608","doi":"10.1609/aaai.v31i1.10848","title":"Fast Generalized Distillation for Semi-Supervised Domain Adaptation","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Domain adaptation; Computer science; Distillation; Labeled data; Support vector machine; Classifier (UML); Transfer of learning; Artificial intelligence; Machine learning; Adaptation (eye); Domain (mathematical analysis); Data source; Data mining; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002713657,0.001260473,0.001765735,0.0008641449,0.0008599643,0.0009272521,0.002719223,0.001532696,0.002093257],"category_scores_gemma":[0.006677892,0.0006553743,0.001096734,0.001190354,0.001557595,0.002708793,0.003498862,0.003599707,0.0009795335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007547264,"about_ca_system_score_gemma":0.001447861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002755516,"about_ca_topic_score_gemma":0.003784607,"domain_scores_codex":[0.9975097,0.001020031,0.0001208359,0.0007550202,0.0004403637,0.0001541204],"domain_scores_gemma":[0.9964651,0.001720609,0.0002274566,0.000897004,0.00052448,0.0001653314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004631872,0.000383419,0.001354901,0.0002979703,0.0002005383,0.0001827049,0.0003262794,0.346393,0.01959972,0.01712892,0.00907892,0.6045905],"study_design_scores_gemma":[0.00001011604,0.00002779167,0.0001050233,0.000004140882,0.000005109105,0.00002753782,0.00001244116,0.9886721,0.001757674,0.008807437,0.0005609689,0.000009625084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01396174,0.0003188365,0.9832154,0.0001534654,0.00005450104,0.00006148861,0.00009916451,0.001577172,0.0005582935],"genre_scores_gemma":[0.5235698,0.0003214925,0.4706346,0.0005073583,0.0001427638,0.0003583656,0.001304182,0.000311463,0.002849993],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002755516,"threshold_uncertainty_score":0.01435131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1200807611652184,"score_gpt":0.3188042640720414,"score_spread":0.198723502906823,"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."}}