{"id":"W2736352281","doi":"10.1109/cvprw.2017.78","title":"Deep LDA-Pruned Nets for Efficient Facial Gender Classification","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pruning; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Decorrelation; Linear discriminant analysis; Support vector machine; Reduction (mathematics); Layer (electronics); Machine learning; Algorithm; Mathematics","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":[0.0002747689,0.0007444506,0.0004347434,0.0004449558,0.000258303,0.0003701933,0.0008207967,0.0004225268,0.003886023],"category_scores_gemma":[0.0006367936,0.0002678115,0.0003529896,0.0003964775,0.0002101258,0.0005610411,0.0005607458,0.000707256,0.002168691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005691034,"about_ca_system_score_gemma":0.0006490484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006631374,"about_ca_topic_score_gemma":0.01539975,"domain_scores_codex":[0.9998598,0.00001645392,0.000005019683,0.00003412932,0.00004273132,0.00004179499],"domain_scores_gemma":[0.9998949,0.00002443062,0.00001188402,0.00003139624,0.00002761905,0.000009757549],"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":[0.0005233513,0.0001530043,0.002837035,0.0001166906,0.00008365192,0.0002245788,0.00008615034,0.1083767,0.06712359,0.005273185,0.01493161,0.8002704],"study_design_scores_gemma":[0.00001904334,0.00007090475,0.0019589,0.00002213835,0.00002797727,0.000133547,0.00003107411,0.9603209,0.02778209,0.004145406,0.005475149,0.00001282077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2004548,0.001734532,0.7779518,0.0003779818,0.0002477147,0.00009775071,0.001387057,0.009919489,0.007828832],"genre_scores_gemma":[0.7234555,0.0005158142,0.2504449,0.0002837917,0.00005400086,0.0001225172,0.003057918,0.0003463665,0.0217193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006631374,"threshold_uncertainty_score":0.01318556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1000864213931217,"score_gpt":0.3215700067969769,"score_spread":0.2214835854038552,"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."}}