{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007647743,0.001233872,0.0005961711,0.0003502248,0.0003497077,0.0005936389,0.001899591,0.0008374729,0.004250835],"category_scores_gemma":[0.001741907,0.0006316277,0.0004025057,0.0003320356,0.0007239273,0.002229672,0.001307978,0.0012998,0.001160839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000512764,"about_ca_system_score_gemma":0.0009379305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002234423,"about_ca_topic_score_gemma":0.006344077,"domain_scores_codex":[0.9997075,0.00007530191,0.00001636494,0.0000965391,0.00006027176,0.00004397364],"domain_scores_gemma":[0.9995183,0.0001886412,0.00003735881,0.0001270823,0.00009187256,0.00003675577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003608553,0.0002708642,0.001530101,0.0002055801,0.0001363457,0.0002017164,0.0001589255,0.7183419,0.02765532,0.01607074,0.006848576,0.228219],"study_design_scores_gemma":[0.0000201812,0.0000868454,0.00009411592,0.000008488425,0.00001066674,0.00003300545,0.00001289662,0.9896865,0.005662373,0.003339048,0.00104106,0.000004724421],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0419478,0.0004376055,0.9505666,0.0002075634,0.00007801403,0.000113305,0.00012261,0.002797099,0.003729435],"genre_scores_gemma":[0.5713556,0.0002549638,0.4203323,0.0004876218,0.00006027556,0.000359546,0.0005975661,0.000505473,0.006046542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004250835,"threshold_uncertainty_score":0.01422042,"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."}}