{"id":"W1534189005","doi":"10.1007/11427445_115","title":"Adaptive Constructive Neural Networks Using Hermite Polynomials for Image Compression","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Hermite polynomials; Constructive; Image compression; Artificial neural network; Artificial intelligence; Data compression; Image (mathematics); Computer vision; Algorithm; Image processing; Mathematics; Pure mathematics; Programming language","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":[0.0006439901,0.0008625807,0.0009597572,0.0008296502,0.0005300909,0.0005750741,0.004307863,0.0004951719,0.0000175998],"category_scores_gemma":[0.0000963363,0.00079156,0.0002396401,0.0004912351,0.001380177,0.002088394,0.003098878,0.001076914,0.000004421745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005369188,"about_ca_system_score_gemma":0.0003681404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001548414,"about_ca_topic_score_gemma":0.00001340357,"domain_scores_codex":[0.9949594,0.00008036404,0.0008509028,0.002269737,0.00082364,0.001015918],"domain_scores_gemma":[0.9954333,0.00108121,0.0008111232,0.001900709,0.0005079147,0.0002658004],"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":[0.00004190267,0.00002590178,0.000006322055,0.00001831806,0.00001398786,0.00004869443,0.0001374714,0.1492963,0.001249793,0.007733437,0.00008052892,0.8413473],"study_design_scores_gemma":[0.000398516,0.0001689463,0.00001095377,0.0005244961,0.00001235557,0.0001410636,2.312474e-7,0.9421769,0.006073708,0.04893168,0.0007243155,0.0008368061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000293455,0.0007034306,0.995123,0.0001766134,0.001629143,0.001306499,0.00007188761,0.000437833,0.0005222936],"genre_scores_gemma":[0.03247419,0.00003333245,0.9654144,0.0009514802,0.0009375844,0.00003071706,0.00001723891,0.00006899017,0.00007203607],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8405105,"threshold_uncertainty_score":0.9994535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02542618094314895,"score_gpt":0.2912761856900123,"score_spread":0.2658500047468633,"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."}}