{"id":"W3080224235","doi":"10.1109/tnnls.2020.3016688","title":"Parameter-Efficient Deep Neural Networks With Bilinear Projections","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Australian Research Council; Canadian Institute for Advanced Research; Nvidia","keywords":"Redundancy (engineering); Bilinear interpolation; Computer science; Projection (relational algebra); Deep neural networks; Benchmark (surveying); Deep learning; Algorithm; Artificial neural network; Artificial intelligence; Computer vision","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001778187,0.0004290482,0.0004213981,0.0001165997,0.001161626,0.0004171927,0.0004838147,0.0001540903,0.000005257635],"category_scores_gemma":[0.00001121031,0.0003523315,0.0001284037,0.001466127,0.000141654,0.0003293979,0.00001286417,0.001561968,0.000007974357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004364319,"about_ca_system_score_gemma":0.00001653225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003843463,"about_ca_topic_score_gemma":0.00001489293,"domain_scores_codex":[0.9971144,0.000386247,0.0004911051,0.001001175,0.0003422759,0.0006647711],"domain_scores_gemma":[0.9981494,0.0006000632,0.0002373707,0.0004967136,0.0001092941,0.0004071681],"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":[0.00005614328,0.00006137118,0.00006658291,0.00001615088,0.0000328198,0.00001607645,0.0002106407,0.9718103,0.00002257996,0.0001430157,0.00003112305,0.02753314],"study_design_scores_gemma":[0.0004620684,0.0007575405,0.0000639505,0.00003210224,0.00003733694,0.0001606169,0.0001182138,0.9971423,0.00001576229,0.000002043166,0.0008071303,0.0004009251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02220249,0.0004410029,0.9737113,0.001113507,0.0007252818,0.0009142553,0.000002194742,0.0008495296,0.00004042976],"genre_scores_gemma":[0.996012,0.00006155305,0.002570343,0.0005404782,0.0003858958,0.0002651887,0.000004053721,0.00005778252,0.0001027182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9738095,"threshold_uncertainty_score":0.9998929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0184000669542036,"score_gpt":0.2324742499482307,"score_spread":0.2140741829940271,"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."}}