{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00128065,0.000578152,0.0008558691,0.000367756,0.00076216,0.000535741,0.002729931,0.000268454,0.000004105855],"category_scores_gemma":[0.0002945511,0.0005890845,0.0004921622,0.002669403,0.0000914002,0.0004384471,0.001170406,0.0007815837,0.0000136532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003681788,"about_ca_system_score_gemma":0.0001248372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003275008,"about_ca_topic_score_gemma":0.00001150472,"domain_scores_codex":[0.9952291,0.0004730283,0.0009679546,0.001626819,0.0004040817,0.001299069],"domain_scores_gemma":[0.9939037,0.003135954,0.0004717823,0.001804468,0.0003678575,0.0003162286],"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":[0.00004206286,0.0001368818,0.00007980424,0.00007025356,0.00008184117,0.000009107549,0.0002143165,0.369465,0.0002414721,0.1670533,0.0008080769,0.4617979],"study_design_scores_gemma":[0.0008293723,0.0001455016,0.0005676828,0.0001235922,0.00006789635,0.00003257729,0.00002473564,0.9710529,0.0001015006,0.01311563,0.01341755,0.0005210981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00160543,0.002023585,0.9910845,0.00127007,0.0004259558,0.002440461,0.000006704547,0.0007639469,0.0003793117],"genre_scores_gemma":[0.6138083,0.00003495763,0.3820161,0.00317267,0.0002005936,0.0006045528,0.00001789708,0.00005325442,0.00009167635],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6122028,"threshold_uncertainty_score":0.9996561,"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."}}