{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004077802,0.000476531,0.000479789,0.00007432783,0.0006361308,0.0003646988,0.001787477,0.0001912553,0.000008021635],"category_scores_gemma":[0.00002490829,0.0003241849,0.0001218371,0.000454296,0.0001839242,0.0001201592,0.001101129,0.000661746,0.000008251589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009261238,"about_ca_system_score_gemma":0.00005272995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002405215,"about_ca_topic_score_gemma":0.00003486574,"domain_scores_codex":[0.9975742,0.0001848443,0.000436967,0.001041812,0.0002502916,0.0005118645],"domain_scores_gemma":[0.9955046,0.002165522,0.0003825794,0.001550012,0.0002570403,0.0001402014],"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":[0.00001733073,0.00004309021,0.00003122813,0.0000156178,0.00004585389,0.000001058107,0.000175275,0.9752102,0.00004561644,0.008243621,0.001350104,0.01482103],"study_design_scores_gemma":[0.0003614376,0.0001097876,0.000522371,0.00001653853,0.00003761253,0.000009289298,0.00001584256,0.9941314,0.0001405793,0.003604751,0.0006684714,0.0003819563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003677423,0.003518533,0.9882429,0.002116673,0.0006907207,0.004517219,0.00001816458,0.0002621077,0.00026591],"genre_scores_gemma":[0.9389368,0.0001047769,0.05912445,0.0008062799,0.0002548319,0.0004940742,0.00004125693,0.00004448601,0.00019309],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.938569,"threshold_uncertainty_score":0.999921,"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."}}