{"id":"W4386735373","doi":"10.1007/978-3-031-43520-1_16","title":"Learning Sparse Fully Connected Layers in Convolutional Neural Networks","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Convolutional neural network; Computer science; Regularization (linguistics); Deep learning; Smoothing; Artificial intelligence; Simple (philosophy); Pattern recognition (psychology)","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":[0.0004393434,0.0005861747,0.0008122402,0.00032692,0.0002034605,0.0002213626,0.000662012,0.0008075296,0.000007255913],"category_scores_gemma":[0.00007837691,0.0005782111,0.0001150291,0.0005401342,0.0001436092,0.000176401,0.0003680278,0.002098429,0.00001181365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001600351,"about_ca_system_score_gemma":0.00004746978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006714143,"about_ca_topic_score_gemma":0.0005923284,"domain_scores_codex":[0.9968104,0.0001628193,0.0008246531,0.001096967,0.0003465625,0.0007586312],"domain_scores_gemma":[0.9970737,0.001656445,0.000424092,0.0005868253,0.00009854383,0.0001603874],"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":[0.00001490454,0.00000604323,0.0005962647,0.00002485821,0.00002168703,0.00009549326,0.00007301547,0.9261825,0.000001909201,0.06310028,0.000144997,0.009738035],"study_design_scores_gemma":[0.0003961612,0.00007296589,0.0003760559,0.0004192821,0.00001092229,0.00007441101,0.000003567096,0.9860589,1.801875e-7,0.00732804,0.004705315,0.0005541896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002654256,0.008673746,0.9839807,0.0004717236,0.00196066,0.001104469,0.000006772299,0.0004586096,0.003077919],"genre_scores_gemma":[0.9903372,0.001361118,0.000737657,0.0003326897,0.00145156,0.0001606003,0.0001432599,0.000133165,0.005342743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9900718,"threshold_uncertainty_score":0.9996669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02260350280409537,"score_gpt":0.2374920410279028,"score_spread":0.2148885382238075,"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."}}