{"id":"W4390129274","doi":"10.1016/j.knosys.2023.111327","title":"Sparse smooth group <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si275.svg\" display=\"inline\" id=\"d1e17665\"><mml:mrow><mml:msub><mml:mrow><mml:mi>L</mml:mi></mml:mrow><mml:mrow><mml:mn>0</mml:mn></mml:mrow></mml:msub><mml:mo>∘</mml:mo><mml:msub><mml:mrow><mml:mi>L</mml:mi></mml:mrow><mml:mrow><mml:mn>1</mml:mn><mml:mo>/</mml:mo><mml:mn>2</mml:mn></mml:mrow></mml:msub></mml:mrow></mml:math> regularization method for convolutional neural networks","year":2023,"lang":"lv","type":"article","venue":"Knowledge-Based Systems","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Regularization (linguistics); Convolutional neural network; Benchmark (surveying); Computer science; Algorithm; Function (biology); Group (periodic table); Artificial neural network; Artificial intelligence","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","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"category_scores_codex":[0.007750067,0.003432633,0.001361849,0.002934793,0.005155721,0.005507399,0.007389166,0.009206227,0.737192],"category_scores_gemma":[0.005563019,0.007455555,0.006798467,0.005719718,0.004782383,0.0043563,0.005549941,0.005988565,0.005227275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001085243,"about_ca_system_score_gemma":0.005174058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005822212,"about_ca_topic_score_gemma":0.006282914,"domain_scores_codex":[0.9683291,0.002743358,0.006683559,0.006273941,0.007353805,0.008616216],"domain_scores_gemma":[0.9739823,0.007035613,0.006742282,0.007075271,0.001065035,0.004099526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004466868,0.0009082831,0.00003979627,0.004504006,0.005464755,0.003333342,0.002619462,0.02613256,0.007278746,0.2262204,0.7150117,0.004020056],"study_design_scores_gemma":[0.00547583,0.003784409,0.0001449662,0.005053583,0.004966471,0.003414853,0.003092778,0.1618531,0.791045,0.0002713657,0.01517671,0.005720964],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1177774,0.008205015,0.02178317,0.001584054,0.01662891,0.0002969657,0.00248682,0.002222042,0.8290156],"genre_scores_gemma":[0.9530578,0.002899406,0.007819666,0.002740347,0.009884872,0.007122715,0.01074827,0.004332387,0.001394568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8352804,"threshold_uncertainty_score":0.9979813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02289700021035126,"score_gpt":0.2510226319587269,"score_spread":0.2281256317483757,"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."}}