{"id":"W3043656308","doi":"10.3390/iot2020012","title":"ThriftyNets: Convolutional Neural Networks with Tiny Parameter Budget","year":2021,"lang":"en","type":"preprint","venue":"IoT","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Convolutional neural network; Normalization (sociology); Computer science; Computation; Upsampling; Complement (music); Factorization; Algorithm; Artificial intelligence; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009977922,0.000376607,0.000372455,0.00006192353,0.0001663451,0.000320063,0.001439541,0.0002441142,0.00003770868],"category_scores_gemma":[0.00002313409,0.0003362446,0.0001350885,0.0003636809,0.0001471954,0.0001612449,0.001738167,0.001074838,0.00002547693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007617491,"about_ca_system_score_gemma":0.0001349926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001569547,"about_ca_topic_score_gemma":0.00002405688,"domain_scores_codex":[0.9975464,0.0001014443,0.0003409405,0.001116273,0.0003929915,0.0005020009],"domain_scores_gemma":[0.9974791,0.0003274833,0.0002638933,0.001588032,0.0001764664,0.0001650537],"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":[0.00001359319,0.00008847733,0.0008061918,0.00002289559,0.00007382853,0.00007910854,0.000100742,0.9681058,0.00002692176,0.01221263,0.003109561,0.01536024],"study_design_scores_gemma":[0.0002308513,0.00004802122,0.002665078,0.00007522274,0.00002046357,0.00009586308,0.000006230978,0.9876479,0.00005942922,0.003545184,0.005097864,0.0005078964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01433769,0.001249047,0.9799097,0.002160938,0.0008518537,0.0004671474,0.0000110145,0.000386024,0.0006266267],"genre_scores_gemma":[0.7860474,0.0000621296,0.2108556,0.001764357,0.0005523121,0.0002992875,0.000129478,0.00004026519,0.0002491071],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7717097,"threshold_uncertainty_score":0.999909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01874690361588241,"score_gpt":0.2574461907209802,"score_spread":0.2386992871050978,"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."}}