{"id":"W2740333758","doi":"10.24963/ijcai.2017/352","title":"Learning Feature Engineering for Classification","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature engineering; Feature (linguistics); Computer science; Feature selection; Artificial intelligence; Feature vector; Machine learning; Transformation (genetics); Aggregate (composite); Set (abstract data type); Artificial neural network; Process (computing); Data mining; Pattern recognition (psychology); Deep learning","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00285409,0.002138925,0.001512761,0.003362869,0.0006681767,0.001670084,0.00184614,0.001365755,0.002931072],"category_scores_gemma":[0.01489632,0.0004311401,0.001708967,0.00320961,0.001032304,0.003000912,0.001691467,0.002781697,0.001998874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076173,"about_ca_system_score_gemma":0.001276334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002405414,"about_ca_topic_score_gemma":0.00306387,"domain_scores_codex":[0.9974371,0.0007423261,0.0002288519,0.0008463067,0.0005973463,0.0001479558],"domain_scores_gemma":[0.9935661,0.003697731,0.0005259338,0.001304735,0.0007946849,0.0001109265],"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":[0.0002536078,0.0003389782,0.007504433,0.0004273543,0.0002001069,0.0001495385,0.0001291835,0.1352067,0.00810233,0.0147477,0.01705341,0.8158866],"study_design_scores_gemma":[0.00004116557,0.0001639375,0.001381531,0.00006348327,0.00004968908,0.0001358974,0.00006109448,0.9301842,0.006521249,0.05252884,0.008830156,0.00003862282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01697602,0.0008882463,0.9750992,0.0004843797,0.0000804936,0.0001600162,0.0009727722,0.003805742,0.001533082],"genre_scores_gemma":[0.3136094,0.0007152075,0.6773009,0.0003800904,0.0001756193,0.0006577505,0.00521054,0.0003729555,0.00157751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003362869,"threshold_uncertainty_score":0.0150941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02701836804495996,"score_gpt":0.2871792180817002,"score_spread":0.2601608500367402,"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."}}