{"id":"W2096356503","doi":"10.1007/s00500-006-0052-z","title":"Image Compression and Reconstruction Using pi t -Sigma Neural Networks","year":2006,"lang":"en","type":"article","venue":"Soft Computing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial neural network; Feedforward neural network; Perceptron; Algorithm; Computer science; Convergence (economics); Multilayer perceptron; Mean squared error; Conjugate gradient method; Feed forward; Backpropagation; Layer (electronics); Lossy compression; Image compression; Sigma; Pattern recognition (psychology); Artificial intelligence; Mathematics; Image (mathematics); Image processing; Physics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001200298,0.0001213678,0.0001250776,0.00004302569,0.0004665075,0.0002556969,0.0002355324,0.00004728878,0.000001879449],"category_scores_gemma":[0.00000414908,0.0001160077,0.00003666896,0.0002712585,0.00006315723,0.0003092678,0.000273768,0.0001666625,0.000001233032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001744632,"about_ca_system_score_gemma":0.000007753511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006951436,"about_ca_topic_score_gemma":0.000003389709,"domain_scores_codex":[0.999018,0.00004637285,0.0002254435,0.0003459135,0.00009838642,0.0002659124],"domain_scores_gemma":[0.9994332,0.0001079876,0.0001285644,0.0002314013,0.00004454283,0.00005427084],"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":[0.000003719551,0.00003955989,0.008186227,0.00001613872,0.000006574884,0.0000109621,0.00005988048,0.3624159,0.01091178,0.008169902,0.0007183537,0.6094609],"study_design_scores_gemma":[0.0001345208,0.000009118951,0.003756245,0.00003318895,0.000003528707,0.00012895,0.000005389657,0.9939327,0.0001194167,0.001621431,0.0001227581,0.0001327341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3016342,0.0001617176,0.6973414,0.0001546869,0.0002693693,0.00008193414,2.567682e-7,0.0001617072,0.000194687],"genre_scores_gemma":[0.8912702,0.000002653139,0.1081638,0.0001037299,0.0004384545,0.000001090457,0.000002147097,0.000008220421,0.000009669656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6315168,"threshold_uncertainty_score":0.4730656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01259578683317587,"score_gpt":0.2415659570232043,"score_spread":0.2289701701900285,"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."}}