{"id":"W4412604667","doi":"10.5753/reic.2025.6038","title":"Deep GreenAI: Effective Layer Pruning Method for Modern Neural Networks","year":2025,"lang":"en","type":"article","venue":"Revista Eletrônica de Iniciação Científica em Computação","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo; Institute for Catastrophic Loss Reduction","keywords":"Pruning; Layer (electronics); Artificial neural network; Computer science; Artificial intelligence; Deep neural networks; Biology; Materials science; Nanotechnology; Botany","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001211367,0.001313944,0.001028979,0.001131569,0.0006055586,0.001138602,0.002182729,0.001423406,0.002720698],"category_scores_gemma":[0.004102424,0.0005412594,0.0009153308,0.0007662245,0.0005974672,0.001662115,0.001459516,0.002554678,0.0009395199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000885718,"about_ca_system_score_gemma":0.001429051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004926176,"about_ca_topic_score_gemma":0.009171793,"domain_scores_codex":[0.999339,0.000119605,0.00004389187,0.0001045011,0.0003102592,0.00008274489],"domain_scores_gemma":[0.9991033,0.0003471905,0.0001099231,0.0001853278,0.0002052918,0.00004891953],"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":[0.0002138786,0.0001087324,0.001493547,0.0002401648,0.0001751931,0.0002538407,0.0001799401,0.4824374,0.01817538,0.02570447,0.00953199,0.4614855],"study_design_scores_gemma":[0.000009792332,0.00002579372,0.0001404679,0.00001916478,0.00001550887,0.0000419861,0.000009300674,0.9880875,0.003572064,0.006260029,0.001811494,0.000006956987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01644787,0.0008537793,0.9783199,0.0002141408,0.00007986975,0.0000543069,0.0001219272,0.002227748,0.001680547],"genre_scores_gemma":[0.3218921,0.001006461,0.6686275,0.0003843317,0.0001274411,0.0002890168,0.0008140905,0.0006915249,0.006167519],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004926176,"threshold_uncertainty_score":0.00979501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01971982093158983,"score_gpt":0.3252183285404317,"score_spread":0.3054985076088419,"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."}}