{"id":"W2134862753","doi":"10.1007/978-3-540-87536-9_99","title":"Analysis-by-Synthesis by Learning to Invert Generative Black Boxes","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Face recognition and analysis","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Computer science; Generative model; Artificial neural network; Set (abstract data type); Artificial intelligence; Black box; Graphics; Generative Design; Machine learning; Computer graphics (images); Compatibility (geochemistry); Programming language","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":[0.001125013,0.001267725,0.0008483766,0.0006351238,0.0005187691,0.001307448,0.001373199,0.001195184,0.01168457],"category_scores_gemma":[0.00356105,0.0008803185,0.001789905,0.0004400507,0.001730239,0.002103385,0.002540299,0.002215639,0.003835244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004492681,"about_ca_system_score_gemma":0.0006318204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006190013,"about_ca_topic_score_gemma":0.001163463,"domain_scores_codex":[0.9993641,0.0002079737,0.00003030145,0.0001864534,0.0001498348,0.00006139973],"domain_scores_gemma":[0.9981356,0.001247481,0.00005812053,0.0003918815,0.0001201208,0.00004684957],"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":[0.0002546247,0.00009135454,0.0007818296,0.0002869276,0.0001238389,0.0002475478,0.0004952999,0.1741443,0.03536577,0.1798438,0.004872651,0.6034921],"study_design_scores_gemma":[0.00002814726,0.00005762185,0.00008378039,0.00003472158,0.0000502765,0.0001445789,0.00005426609,0.7848771,0.01962527,0.1878621,0.007159617,0.00002256674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002323385,0.00004400622,0.9947022,0.00004802181,0.00002603397,0.00001883695,0.00001415477,0.0009568825,0.001866503],"genre_scores_gemma":[0.1801617,0.000218165,0.8090312,0.0001833184,0.00008357941,0.0001563185,0.0001891069,0.001268851,0.008707784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01168457,"threshold_uncertainty_score":0.03908879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01524933951670038,"score_gpt":0.2336942533400051,"score_spread":0.2184449138233047,"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."}}