{"id":"W2971130703","doi":"10.1109/tpami.2019.2937294","title":"Deep Differentiable Random Forests for Age Estimation","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Face recognition and analysis","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University Health Network","funders":"National Natural Science Foundation of China","keywords":"Deep learning; Differentiable function; Random forest; Regression; Pattern recognition (psychology); Feature (linguistics); Convolutional neural network; Tree (set theory)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001917802,0.0001933065,0.0003738562,0.0005428857,0.0001654245,0.0002161135,0.0003039708,0.00005944331,0.0003293914],"category_scores_gemma":[0.000004964802,0.0001628183,0.0004237858,0.0008211344,0.00002770637,0.0002689755,0.000003958914,0.0001277112,0.0000938833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002215019,"about_ca_system_score_gemma":0.000009485912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002323289,"about_ca_topic_score_gemma":0.001683174,"domain_scores_codex":[0.9986908,0.00005451178,0.0003293594,0.0004843202,0.0002164532,0.0002245055],"domain_scores_gemma":[0.9991117,0.0002072069,0.00009963158,0.0003972859,0.00007558099,0.0001085665],"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":[0.00002164993,0.0001437982,0.0007602433,0.00003581511,0.0006393417,0.000002020119,0.0001640247,0.1892721,0.000198971,0.0001083773,0.000006702444,0.808647],"study_design_scores_gemma":[0.000315455,0.00008111536,0.0005538957,0.00001640869,0.0004912724,0.000002304984,0.00001931165,0.9693375,0.02809025,0.0008597784,0.00003521425,0.0001975486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005759593,0.00004733535,0.9934161,0.0002321328,0.0001321968,0.0002546717,0.0000199868,0.00007729043,0.00006071746],"genre_scores_gemma":[0.9933481,0.0001132815,0.005405256,0.0002503955,0.000008311883,0.00005520774,0.00002406772,0.000009500449,0.0007859205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9880108,"threshold_uncertainty_score":0.6639538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01582440736541821,"score_gpt":0.2618737843582439,"score_spread":0.2460493769928257,"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."}}