{"id":"W2157849268","doi":"10.1109/icip.1996.560848","title":"A simple feedforward neural network architecture for 3-D motion and structure estimation","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Feed forward; Feedforward neural network; Computer science; Artificial neural network; Spurious relationship; Simple (philosophy); Probabilistic neural network; Physical neural network; Time delay neural network; Control theory (sociology); Motion estimation; Motion (physics); Focus (optics); Artificial intelligence; Control engineering; Control (management); Machine learning; 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":[0.0003359506,0.0005066458,0.0003657017,0.0002606701,0.0002767006,0.0003298765,0.0009151471,0.000943381,0.002873444],"category_scores_gemma":[0.0007095609,0.0002682932,0.0002844664,0.0003741133,0.0002561939,0.0007202601,0.0004177554,0.0005780656,0.0008962345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003076281,"about_ca_system_score_gemma":0.0004690194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001708336,"about_ca_topic_score_gemma":0.00405031,"domain_scores_codex":[0.9998672,0.00001692065,0.000007796791,0.00003092892,0.00006238751,0.00001482295],"domain_scores_gemma":[0.9998727,0.00003450455,0.00001180881,0.00001626988,0.00005344607,0.00001137824],"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":[0.0002372033,0.0001266815,0.0008831509,0.0004694684,0.00009104237,0.0002978594,0.00006760251,0.270094,0.1479964,0.02219319,0.006478605,0.5510647],"study_design_scores_gemma":[0.00003501118,0.000176671,0.0009105164,0.00002883401,0.00003360095,0.0001854367,0.000004727568,0.9668244,0.01425695,0.008883473,0.0086295,0.00003085376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006432123,0.0003216982,0.9902018,0.0001027771,0.0001182762,0.00004198915,0.00009385667,0.0007558181,0.00193167],"genre_scores_gemma":[0.3060101,0.0006952675,0.68231,0.0002189336,0.000153109,0.0002813891,0.000362945,0.00005791241,0.009910429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002873444,"threshold_uncertainty_score":0.00961262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01342412525887193,"score_gpt":0.2575134251783463,"score_spread":0.2440892999194744,"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."}}