{"id":"W2964282938","doi":"10.5244/c.31.115","title":"Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Pruning; Computer science; Convolutional neural network; Parameterized complexity; Artificial intelligence; Set (abstract data type); Domain (mathematical analysis); Bayesian optimization; Fine-tuning; Pattern recognition (psychology); Network architecture; Machine learning; Algorithm; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002825378,0.0002632664,0.0004317774,0.0001090495,0.0002408873,0.000191192,0.0006990889,0.0001805304,0.00001837597],"category_scores_gemma":[0.00007672271,0.0002078626,0.00005899578,0.0001060706,0.0001685978,0.0004461247,0.001829984,0.0003920277,4.286678e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003098843,"about_ca_system_score_gemma":0.0001578616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004183764,"about_ca_topic_score_gemma":0.00000957797,"domain_scores_codex":[0.9984842,0.00006200452,0.000350401,0.0005576639,0.0003070567,0.0002387029],"domain_scores_gemma":[0.9980354,0.00007517813,0.0006214363,0.0008907844,0.000284563,0.00009262098],"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":[0.0001522947,0.0001451477,0.004891132,0.0006278761,0.0001663338,0.00006195906,0.0004969382,0.8605188,0.001007752,0.05648725,0.005593585,0.06985094],"study_design_scores_gemma":[0.0003580526,0.0001612837,0.001167215,0.001470734,0.00001960597,0.00002358789,0.000004651092,0.9775459,0.004328433,0.01413034,0.0004197918,0.0003704207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002008528,0.0006249915,0.9956391,0.0003433231,0.0001215057,0.0003288368,0.000004615436,0.000235757,0.002501049],"genre_scores_gemma":[0.2005529,0.0001255393,0.7988646,0.00003782165,0.00008536324,0.00001657799,0.0000285256,0.00001517751,0.0002734839],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.200352,"threshold_uncertainty_score":0.847639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03132777153801756,"score_gpt":0.2813944063674761,"score_spread":0.2500666348294585,"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."}}