{"id":"W2119586505","doi":"10.1109/tsmcb.2004.825930","title":"Facial Expression Recognition Using Constructive Feedforward Neural Networks","year":2004,"lang":"en","type":"letter","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":246,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Instituto de Telecomunicações","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Facial expression; Sadness; Artificial neural network; Feedforward neural network; Facial recognition system; Feature (linguistics); Feed forward; Speech recognition; Anger; Psychology","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":[0.0007595993,0.0009668879,0.0005303149,0.0005988551,0.0002408125,0.0004624043,0.001379382,0.0005218859,0.0009814636],"category_scores_gemma":[0.002177757,0.0004034516,0.0006769277,0.0004237868,0.0005032315,0.0006837457,0.000688465,0.0006984444,0.0004154037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003500433,"about_ca_system_score_gemma":0.000335714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001643935,"about_ca_topic_score_gemma":0.002239774,"domain_scores_codex":[0.99942,0.0001451587,0.00002945783,0.00009593552,0.0002583388,0.00005116219],"domain_scores_gemma":[0.9993099,0.0002969374,0.00008046774,0.00006753147,0.0002278355,0.00001736134],"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":[0.0002110276,0.0001528494,0.001028385,0.0001627385,0.0001233183,0.0002762042,0.0001245128,0.2508861,0.08238865,0.004778752,0.001861046,0.6580064],"study_design_scores_gemma":[0.00000668443,0.00006776979,0.0003147274,0.00001035554,0.00002186779,0.00008100431,0.000007804463,0.9818148,0.0159324,0.001153215,0.0005792414,0.00001015066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01384004,0.0001950399,0.9836024,0.00005878165,0.00005471188,0.00004405436,0.00002039678,0.0008655984,0.001318864],"genre_scores_gemma":[0.5109656,0.0005327659,0.4839249,0.0002510459,0.00008833535,0.0002174396,0.0002119265,0.00008131682,0.003726573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001643935,"threshold_uncertainty_score":0.004017234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03180820635967933,"score_gpt":0.2369692993113068,"score_spread":0.2051610929516274,"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."}}