{"id":"W1990838225","doi":"10.1117/12.421169","title":"<title>Moving image compression and generalization capability of constructive neural networks</title>","year":2001,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Generalization; Constructive; Artificial intelligence; Artificial neural network; Similarity (geometry); Computer vision; Data compression; Image compression; Pattern recognition (psychology); Feed forward; Image (mathematics); Backpropagation; Image processing; Mathematics; Engineering","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":[0.0005982663,0.0004809636,0.0003195108,0.0004110054,0.0001525125,0.0004074997,0.0004811345,0.0003568614,0.00254871],"category_scores_gemma":[0.003084825,0.00009764973,0.000233427,0.0003943102,0.0005865277,0.0007861471,0.0003390921,0.0004689347,0.0004761213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003262367,"about_ca_system_score_gemma":0.0001382182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001680258,"about_ca_topic_score_gemma":0.001288251,"domain_scores_codex":[0.9997224,0.00006553888,0.00001696893,0.00005410427,0.0001137406,0.0000273417],"domain_scores_gemma":[0.9982305,0.0009314127,0.0002008043,0.000179198,0.0004250155,0.00003310066],"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":[0.0004616581,0.0001133548,0.002432203,0.0002887517,0.00006465017,0.0004172436,0.0001283794,0.2803564,0.1243106,0.01715779,0.004497562,0.5697714],"study_design_scores_gemma":[0.000004368812,0.0001669673,0.001942813,0.00002064308,0.00001561202,0.0001580787,0.00001836285,0.9644269,0.02874339,0.00317259,0.001313133,0.00001721881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3105111,0.003118027,0.6628101,0.00068615,0.0002958772,0.00007749625,0.0001955594,0.001086108,0.02121954],"genre_scores_gemma":[0.9134812,0.00149887,0.07934272,0.0001252269,0.0001217308,0.00005091973,0.0003101983,0.000102794,0.004966344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00254871,"threshold_uncertainty_score":0.008526325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008988659837501913,"score_gpt":0.2235554784595792,"score_spread":0.2145668186220773,"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."}}