{"id":"W1635598920","doi":"","title":"The art of representation: memory reduction and noise tolerance in a neural network vision system","year":2004,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Feature (linguistics); Computer science; Set (abstract data type); Representation (politics); Artificial neural network; Reduction (mathematics); Noise (video); Object (grammar); Generalization; Computer vision; Constraint (computer-aided design); Pattern recognition (psychology); Image (mathematics); 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":[0.0007769454,0.0004648024,0.0005215239,0.0003901101,0.0004049294,0.0009997893,0.001850097,0.001014407,0.001761715],"category_scores_gemma":[0.00279546,0.0003264878,0.0004444837,0.0004204784,0.0007685071,0.002001315,0.001012918,0.001131118,0.0003334437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008682408,"about_ca_system_score_gemma":0.0005613902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004324559,"about_ca_topic_score_gemma":0.003715293,"domain_scores_codex":[0.9996787,0.00005908242,0.0000199045,0.0001020082,0.00009088776,0.00004938339],"domain_scores_gemma":[0.9994067,0.0002597906,0.00006418027,0.0001289527,0.0001160962,0.00002435558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003133932,0.0001063654,0.0007057891,0.0001097125,0.0000720477,0.0001343458,0.000179676,0.6005116,0.02854291,0.02374298,0.002861946,0.3427193],"study_design_scores_gemma":[0.000007055603,0.00003757636,0.0001121415,0.000005433279,0.000009423296,0.00002465462,0.000006221365,0.9911862,0.002971364,0.005004866,0.0006283917,0.000006587774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05885956,0.0006371994,0.9331264,0.0004222135,0.0000915235,0.0000375375,0.00005630657,0.001565345,0.005203898],"genre_scores_gemma":[0.7938001,0.0002786691,0.201025,0.0002764537,0.00007963567,0.00009073212,0.0001033854,0.0001018066,0.004244315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004324559,"threshold_uncertainty_score":0.008598745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01107222238191022,"score_gpt":0.2540711531486056,"score_spread":0.2429989307666953,"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."}}