{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001367941,0.001618292,0.00084205,0.0008826244,0.0003710156,0.001026479,0.0008450147,0.001065067,0.002103259],"category_scores_gemma":[0.005163303,0.0005343797,0.0007258852,0.0009667847,0.001175185,0.001624399,0.001467741,0.002185578,0.001004872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001344674,"about_ca_system_score_gemma":0.001290613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0026252,"about_ca_topic_score_gemma":0.003257696,"domain_scores_codex":[0.9993798,0.0002238465,0.00003742916,0.0001069706,0.0002091429,0.00004277937],"domain_scores_gemma":[0.9990275,0.0004494094,0.0001081342,0.0001257532,0.0002295175,0.00005975394],"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":[0.00007002777,0.00004498331,0.000440414,0.0002350732,0.00006664131,0.00004526631,0.00005610386,0.7437717,0.005113996,0.1526238,0.007504914,0.09002709],"study_design_scores_gemma":[0.000005943501,0.00001812269,0.00006478897,0.00001650291,0.000004366752,0.00001207162,0.000002934048,0.9469189,0.001299668,0.04925267,0.002395696,0.000008276191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001940278,0.0004907277,0.9955516,0.0001584893,0.00004976421,0.00002156771,0.00006278517,0.0003238146,0.001400834],"genre_scores_gemma":[0.2186515,0.001949132,0.7676448,0.0004162237,0.0003258848,0.0004001136,0.0006521545,0.00113738,0.008822809],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0026252,"threshold_uncertainty_score":0.009756386,"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."}}