{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001010206,0.001554501,0.001321036,0.0004818967,0.0004142224,0.001017251,0.00171857,0.001049172,0.003852369],"category_scores_gemma":[0.003350016,0.001258954,0.0009292345,0.0009599549,0.0007829044,0.003260721,0.003438551,0.002888856,0.001983362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008547495,"about_ca_system_score_gemma":0.001858298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004828347,"about_ca_topic_score_gemma":0.005579401,"domain_scores_codex":[0.9992317,0.0001801258,0.00005706691,0.0001693267,0.0002776104,0.00008417181],"domain_scores_gemma":[0.9992291,0.0002742456,0.00006392357,0.0002357991,0.0001455412,0.00005137079],"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":[0.0002522993,0.00007381076,0.0004626891,0.0001639491,0.0000723812,0.0001014751,0.00009771345,0.7741073,0.007803594,0.02201653,0.003757253,0.191091],"study_design_scores_gemma":[0.000006615001,0.00001683279,0.0000293094,0.000004228746,0.000004082028,0.00001472019,0.000004346009,0.990227,0.001232296,0.007977279,0.0004789219,0.000004380546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01212553,0.0004201446,0.9829349,0.0001834111,0.00004665292,0.00003819309,0.0001314398,0.00229247,0.001827298],"genre_scores_gemma":[0.4327269,0.0008507079,0.5581679,0.0002751326,0.00008904691,0.0002909829,0.0008819075,0.0004650421,0.006252317],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004828347,"threshold_uncertainty_score":0.01288748,"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."}}