{"id":"W2165866200","doi":"10.1109/tnn.2002.1031943","title":"Application of adaptive constructive neural networks to image compression","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Constructive; Computer science; Artificial neural network; Quantization (signal processing); Artificial intelligence; Feedforward neural network; Data compression; Image compression; JPEG; Feed forward; Generalization; Image (mathematics); Pattern recognition (psychology); Algorithm; Image processing; Mathematics; Engineering; Control 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001011603,0.0003687807,0.0003951531,0.0001744333,0.0004170938,0.0001037211,0.0009324615,0.0001719281,0.00004803027],"category_scores_gemma":[0.000002143692,0.0003464938,0.0002238009,0.001341965,0.0001811368,0.0005273909,0.00001955855,0.0006582469,0.00002729405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005434147,"about_ca_system_score_gemma":0.000006281912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003742685,"about_ca_topic_score_gemma":0.00001862972,"domain_scores_codex":[0.9976031,0.0001449706,0.0005571339,0.0007876373,0.0003447625,0.0005624],"domain_scores_gemma":[0.998003,0.0003193986,0.0002417761,0.0009409644,0.0001887811,0.0003060581],"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":[0.00003798687,0.0001506932,0.00001087343,0.00000293596,0.00001907003,0.000003493654,0.00006492619,0.7803366,0.0006042231,0.0009428362,0.0008992012,0.2169271],"study_design_scores_gemma":[0.0003887022,0.0002841795,0.000171301,0.00002575999,0.00002501919,0.00003266554,0.00001706581,0.9969817,0.001411498,0.000144496,0.0001898544,0.0003277286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005461358,0.0001118362,0.9911685,0.0009525393,0.0007792987,0.0008999761,0.00002069614,0.0002946095,0.0003111931],"genre_scores_gemma":[0.9893968,0.00005360054,0.009203267,0.0007937323,0.00019526,0.0002410886,0.000003941365,0.00003345327,0.00007887505],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9839354,"threshold_uncertainty_score":0.9998987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01646623996808614,"score_gpt":0.2365681236264005,"score_spread":0.2201018836583144,"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."}}