{"id":"W3080991741","doi":"10.48550/arxiv.2008.10766","title":"Channel-Directed Gradients for Optimization of Convolutional Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Computation; Discretization; Generalization; Benchmark (surveying); Smoothing; Channel (broadcasting); Mathematical optimization; 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":[0.00006447561,0.0001870248,0.0003048729,0.00009698333,0.0001035341,0.00001449965,0.0003058943,0.0002006826,0.00004901748],"category_scores_gemma":[0.00005678456,0.000229127,0.0002214221,0.0002683212,0.00007702009,0.0000550832,0.0001904831,0.0002179401,0.000003002737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007450101,"about_ca_system_score_gemma":0.00003710411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009939165,"about_ca_topic_score_gemma":0.000003115399,"domain_scores_codex":[0.9990372,0.00005412175,0.0002418227,0.0004500556,0.00005006507,0.0001667438],"domain_scores_gemma":[0.998731,0.0001886804,0.0003606286,0.0003109617,0.0003034644,0.0001052355],"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":[0.00006731669,0.0001111944,0.00005348965,0.00009083643,0.00008055128,0.0000027149,0.00004446199,0.8829682,0.000008536895,0.1150691,0.001494624,0.000008911705],"study_design_scores_gemma":[0.0005573332,0.00002788974,0.00009360851,0.00003257882,0.0001565167,0.000001301541,0.00002517446,0.9086574,0.00002478908,0.09020518,0.00003845588,0.0001797505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03393457,0.00001414034,0.964164,0.0001651684,0.0002188544,0.0007391646,0.0002607674,0.0002522027,0.0002512014],"genre_scores_gemma":[0.9915403,0.00002832829,0.007481437,0.00004904427,0.00009652126,0.00000820925,0.0004940195,0.0000269792,0.0002752007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9576057,"threshold_uncertainty_score":0.9343529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1289813507032825,"score_gpt":0.2329301638516703,"score_spread":0.1039488131483877,"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."}}