{"id":"W2973077827","doi":"10.1109/tnnls.2019.2935608","title":"Domain Adaptation With Neural Embedding Matching","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":180,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; National Postdoctoral Program for Innovative Talents; Canada Research Chairs; Natural Science Foundation of Hubei Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Embedding; Computer science; Artificial intelligence; Matching (statistics); Representation (politics); Artificial neural network; Domain (mathematical analysis); Domain adaptation; Feature learning; Generalization; Exploit; Benchmark (surveying); Machine learning; Theoretical computer science; Pattern recognition (psychology); Mathematics; Classifier (UML)","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":[0.001209087,0.000989666,0.001198752,0.001183088,0.0003818006,0.0007444258,0.001873782,0.001281042,0.001349085],"category_scores_gemma":[0.003963045,0.0003468381,0.001185948,0.00146573,0.000723091,0.002631513,0.002001674,0.001867571,0.0007496572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006294622,"about_ca_system_score_gemma":0.0006737531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002192759,"about_ca_topic_score_gemma":0.001777607,"domain_scores_codex":[0.99889,0.0002997234,0.00006310719,0.0004754787,0.0002014298,0.00007026271],"domain_scores_gemma":[0.9989416,0.0003380899,0.0001118228,0.0003423547,0.0002182461,0.00004791904],"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":[0.0001644565,0.000310733,0.002131241,0.0001536272,0.0001847894,0.0001730928,0.0001814894,0.3903069,0.01292236,0.01362157,0.006030254,0.5738196],"study_design_scores_gemma":[0.000008790381,0.00003803086,0.0002829548,0.000006126658,0.00001337751,0.00006324037,0.00002217263,0.9864964,0.002682938,0.009246546,0.001127015,0.00001228277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0136502,0.0003078663,0.9841819,0.00009730237,0.0000467602,0.00005692955,0.00006839551,0.0007064685,0.0008841322],"genre_scores_gemma":[0.5837804,0.0005571345,0.4090032,0.0003929733,0.0001182094,0.0002999933,0.001137058,0.0002121483,0.004498815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002192759,"threshold_uncertainty_score":0.006394327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01161604965998904,"score_gpt":0.2226185692590597,"score_spread":0.2110025195990707,"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."}}