{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006152224,0.0001938923,0.0002256874,0.00009100002,0.0008474677,0.0008012485,0.001953581,0.00008514638,0.00002961031],"category_scores_gemma":[0.0007341164,0.0001549805,0.0001407815,0.000173805,0.0002153621,0.0007534702,0.000237187,0.000159309,0.00003651137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000422938,"about_ca_system_score_gemma":0.00008156241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003781412,"about_ca_topic_score_gemma":0.00001785926,"domain_scores_codex":[0.9983537,0.00001994393,0.0004684036,0.0004500209,0.0004188132,0.0002891452],"domain_scores_gemma":[0.9980103,0.00009156141,0.0006883946,0.0004344733,0.0006901588,0.00008507253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007694187,0.00004271846,0.0001719883,0.00002373348,0.00001037403,1.208995e-7,0.002459163,0.0005171899,0.0283225,0.860449,0.0000536454,0.1078727],"study_design_scores_gemma":[0.0001140302,0.0001241176,0.0012112,0.0001158861,0.000009847875,0.000001572981,0.0008664812,0.6891104,0.06861515,0.2390256,0.0005779669,0.000227753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09098196,0.00001189645,0.8882673,0.005985187,0.0006839925,0.000761995,0.000008348266,0.0001095358,0.01318981],"genre_scores_gemma":[0.9602384,0.00001422348,0.03889633,0.0001601702,0.00009820502,0.00005470091,0.000001870701,0.00001316302,0.0005229571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8692564,"threshold_uncertainty_score":0.7726458,"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."}}