{"id":"W3116512656","doi":"10.1109/ictai50040.2020.00046","title":"Why Layer-Wise Learning is Hard to Scale-up and a Possible Solution via Accelerated Downsampling","year":2020,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Nvidia; National Aeronautics and Space Administration","keywords":"Upsampling; Computer science; Layer (electronics); Feature (linguistics); Artificial intelligence; Convolution (computer science); Feature learning; Deep learning; Scale (ratio); Backpropagation; Machine learning; Artificial neural network; Image (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":[0.000229997,0.0001496115,0.0001643008,0.0001015525,0.0003273732,0.0005698142,0.0003286243,0.00006086165,0.0002119225],"category_scores_gemma":[0.00008771399,0.000145132,0.00004169524,0.0007142929,0.00002124012,0.0006367437,0.0002784654,0.0002416774,0.0003744527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002467248,"about_ca_system_score_gemma":0.00003644996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007310035,"about_ca_topic_score_gemma":0.00001154364,"domain_scores_codex":[0.9986051,0.0000758922,0.0002223559,0.0005194683,0.0002578124,0.0003193145],"domain_scores_gemma":[0.9992537,0.0000565397,0.00006741074,0.0001707264,0.0001078979,0.000343656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001992353,0.0001060779,0.0133426,0.0001277959,0.0001029589,0.00003551962,0.06835084,0.02430917,0.3768263,0.006937813,0.06191137,0.4477504],"study_design_scores_gemma":[0.0005938016,0.0001803063,0.003762459,0.00002407858,0.00000622121,0.00001028202,0.0003281817,0.9259591,0.005666251,0.000168389,0.06298049,0.0003204194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03092974,0.00004551135,0.9477356,0.01811143,0.0001292886,0.0001509763,5.171183e-7,0.0004446634,0.002452285],"genre_scores_gemma":[0.858837,0.00001202598,0.113635,0.02566007,0.00007478801,0.000009962533,0.000003649051,0.00001599553,0.001751466],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.90165,"threshold_uncertainty_score":0.5918313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07194476852431984,"score_gpt":0.2797950632922878,"score_spread":0.207850294767968,"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."}}