{"id":"W2921371084","doi":"10.1109/cvprw.2019.00095","title":"AttoNets: Compact and Efficient Deep Neural Networks for the Edge via Human-Machine Collaborative Design","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Enhanced Data Rates for GSM Evolution; Task (project management); Artificial neural network; Macro; Architecture; Human–machine system; Network architecture; Computer architecture; Network planning and design; Edge device; Machine learning; Distributed computing; Computer engineering; Engineering; Systems engineering; Computer network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000589948,0.0007232964,0.0002546447,0.0002122404,0.0001985093,0.0006816117,0.001397393,0.0005556346,0.00351122],"category_scores_gemma":[0.001107496,0.0003029419,0.0004209145,0.0001539194,0.0005964928,0.001020096,0.0008398475,0.00110972,0.001026407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006428466,"about_ca_system_score_gemma":0.000605537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001058817,"about_ca_topic_score_gemma":0.00355797,"domain_scores_codex":[0.999734,0.00004849358,0.000009480678,0.00005162607,0.0001232303,0.00003315222],"domain_scores_gemma":[0.9997312,0.00008389085,0.00003627927,0.00005471605,0.00006579672,0.00002809692],"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":[0.0001920981,0.0001562436,0.001876707,0.0003494412,0.0001130969,0.0003576793,0.0001994428,0.5698866,0.07162321,0.03480651,0.01399139,0.3064477],"study_design_scores_gemma":[0.00002463842,0.0001956006,0.0003338827,0.00002639387,0.00001895355,0.00008412467,0.0000328085,0.9517025,0.0207827,0.01077609,0.01600632,0.00001603532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03946954,0.0005174243,0.9441392,0.0003766641,0.00009793665,0.000103847,0.0001742689,0.00281301,0.01230811],"genre_scores_gemma":[0.4366209,0.0004686113,0.550088,0.0003850322,0.00002274327,0.0002694732,0.0005426807,0.0004839984,0.01111849],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00351122,"threshold_uncertainty_score":0.01174623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03317335131644809,"score_gpt":0.3065694472637513,"score_spread":0.2733960959473032,"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."}}