{"id":"W2053870179","doi":"10.1142/s0217984901001458","title":"A SIMPLE NEURAL NETWORK APPROACH TO INVARIANT IMAGE RECOGNITION","year":2001,"lang":"en","type":"article","venue":"Modern Physics Letters B","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Artificial neural network; Computer science; Invariant (physics); Artificial intelligence; Pattern recognition (psychology); Time delay neural network; Cellular neural network; Computation; Probabilistic neural network; Image processing; Segmentation; Feature extraction; Computer vision; Image (mathematics); Algorithm; 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":[0.0003426475,0.0005876334,0.0006606753,0.0006883967,0.0002439659,0.0008145808,0.001223607,0.0009791161,0.003910832],"category_scores_gemma":[0.0009533623,0.0002702742,0.0005576789,0.000610391,0.0007267933,0.001404412,0.0007062306,0.000955264,0.001584938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005536756,"about_ca_system_score_gemma":0.0003545098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00137491,"about_ca_topic_score_gemma":0.001368137,"domain_scores_codex":[0.9996578,0.00005692874,0.00001776163,0.00008935834,0.0001476928,0.00003054024],"domain_scores_gemma":[0.9998587,0.00003622138,0.00001411285,0.00003202079,0.00004910138,0.000009887192],"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":[0.0001017781,0.00008666958,0.000524122,0.0003718286,0.0001822396,0.0002581448,0.00007127192,0.2349178,0.04118401,0.2374433,0.004827916,0.480031],"study_design_scores_gemma":[0.0000103654,0.00005334372,0.0003157973,0.0000159773,0.0000267722,0.0001354196,0.000009114067,0.9082369,0.00681391,0.07244328,0.01191207,0.00002698841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002552704,0.0006529517,0.9918793,0.0001287179,0.0001232753,0.00003201042,0.00003985075,0.0004583473,0.004132863],"genre_scores_gemma":[0.2555425,0.002041722,0.7233797,0.0003863157,0.0004344234,0.0002240298,0.0002694279,0.0001583735,0.01756351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003910832,"threshold_uncertainty_score":0.01308304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03106452002172478,"score_gpt":0.2338115315467022,"score_spread":0.2027470115249775,"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."}}