{"id":"W2906164531","doi":"10.15353/jcvis.v4i1.340","title":"MonolithNet: Training monolithic deep neural networks via a partitioned training strategy","year":2018,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"Training (meteorology); Artificial neural network; Computer science; Artificial intelligence; Residual; Deep neural networks; Stochastic gradient descent; Convergence (economics); Deep learning; Gradient descent; Machine learning; Algorithm; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0005351405,0.0001808159,0.0003144525,0.0001976114,0.0003484362,0.0003764851,0.0003750865,0.00004278088,0.000003670853],"category_scores_gemma":[0.00002610985,0.000153418,0.00008291951,0.000392902,0.000128184,0.001073483,0.00006935468,0.0002694507,0.000004249786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004138474,"about_ca_system_score_gemma":0.00006296828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003854369,"about_ca_topic_score_gemma":8.836107e-7,"domain_scores_codex":[0.9981455,0.0001561793,0.0007559046,0.00023694,0.0004006872,0.000304806],"domain_scores_gemma":[0.998201,0.000302994,0.0006177802,0.0001674838,0.0004977106,0.000213079],"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":[0.0000187786,0.00002937151,0.0001726437,0.000008948115,0.00002385022,0.00001707929,0.001983817,0.7776146,0.000175958,0.009887253,0.0002185965,0.2098491],"study_design_scores_gemma":[0.0004667579,0.0001711503,0.003412067,0.0000777805,0.000009301381,0.001204417,0.000413179,0.9778537,0.000005725,0.01575408,0.0004781284,0.0001537801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02577801,0.001077965,0.9711866,0.0009824979,0.0006074852,0.0001337377,8.771935e-7,0.00006223209,0.000170531],"genre_scores_gemma":[0.977879,0.00001340902,0.02095622,0.000371072,0.0007445175,0.000005990933,0.000002735587,0.00001465783,0.00001240694],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.952101,"threshold_uncertainty_score":0.6256204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02980187009467297,"score_gpt":0.2996800737088969,"score_spread":0.269878203614224,"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."}}