{"id":"W4416674895","doi":"10.7717/peerj-cs.3388","title":"Towards optimal sparse CNNs: sparsity-friendly knowledge distillation through feature decoupling","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pooling; Feature (linguistics); Decoupling (probability); Distillation; Artificial neural network; Convolutional neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0009865895,0.001330524,0.001132819,0.0005829684,0.0004272914,0.001018165,0.002023128,0.001223307,0.002340423],"category_scores_gemma":[0.004223955,0.0006078574,0.0007031742,0.0007375418,0.001190107,0.003371757,0.003355808,0.00272027,0.0009365125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006751868,"about_ca_system_score_gemma":0.001433622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002861145,"about_ca_topic_score_gemma":0.005236923,"domain_scores_codex":[0.999487,0.0001092563,0.00002740138,0.0001536518,0.0001377086,0.00008483214],"domain_scores_gemma":[0.9991254,0.0003084159,0.0001044572,0.0002451166,0.000130664,0.00008600046],"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":[0.0003060835,0.0002492146,0.001319564,0.0002360643,0.0001239307,0.0002157124,0.0002360636,0.4753384,0.02969894,0.05031483,0.007530354,0.4344309],"study_design_scores_gemma":[0.00001647412,0.00004190709,0.00007736099,0.000007627788,0.00001185062,0.00003540561,0.00001243968,0.9769746,0.004076012,0.0179093,0.0008287352,0.00000825072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0199917,0.0002008242,0.9767327,0.0002645485,0.00003482414,0.00004302571,0.00009898465,0.001187148,0.00144626],"genre_scores_gemma":[0.5891903,0.0003864857,0.4031794,0.0006473401,0.0001245723,0.0002046765,0.0007452272,0.0003731037,0.005148916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002861145,"threshold_uncertainty_score":0.007829547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02110623592090117,"score_gpt":0.3079105817514071,"score_spread":0.286804345830506,"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."}}