{"id":"W2736761179","doi":"10.1016/j.patcog.2017.07.019","title":"On automated source selection for transfer learning in convolutional neural networks","year":2017,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute on Aging; National Institutes of Health; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; EMS Ingénierie","keywords":"Transfer of learning; Computer science; Convolutional neural network; Artificial intelligence; Selection (genetic algorithm); Machine learning; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0003232537,0.0001085213,0.0001057189,0.0001144774,0.0004830321,0.0002846445,0.0002174513,0.00007875162,0.00003511796],"category_scores_gemma":[0.0001138066,0.0001181709,0.00005735228,0.00007622303,0.00002426901,0.0004404936,0.00002215748,0.0002469505,0.00004238615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004994114,"about_ca_system_score_gemma":0.00001571938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004913558,"about_ca_topic_score_gemma":0.00006735849,"domain_scores_codex":[0.999034,0.0001063882,0.0001820122,0.0002921113,0.0001436953,0.0002417871],"domain_scores_gemma":[0.9995096,0.0001551839,0.00008685501,0.0001221331,0.0000779982,0.00004820436],"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":[0.00005643823,0.00006613548,0.01533414,0.0000159751,0.0000120994,0.000001952673,0.0003771761,0.1171779,0.0002328797,0.0002718757,0.0001318405,0.8663216],"study_design_scores_gemma":[0.0009502988,0.0001256363,0.0488087,0.00004302657,0.000003540515,0.000007457661,0.0000155772,0.9491662,0.00009485463,0.0003752623,0.0002672746,0.0001421706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2344205,0.00000492163,0.7642058,0.0003336541,0.00026397,0.0001749184,0.000001420954,0.0003284896,0.000266345],"genre_scores_gemma":[0.9981327,0.000003156558,0.00109484,0.0004215019,0.0001036065,0.00006368738,0.00005630197,0.0000129665,0.0001112564],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8661794,"threshold_uncertainty_score":0.4818867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03693271865177594,"score_gpt":0.2734762916603086,"score_spread":0.2365435730085326,"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."}}