{"id":"W2939728762","doi":"10.1109/cvprw.2019.00070","title":"Assessing Architectural Similarity in Populations of Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Similarity (geometry); Computer science; Artificial intelligence; Artificial neural network; Selection (genetic algorithm); Process (computing); Architecture; Architectural design; Deep neural networks; Space (punctuation); Machine learning; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.0001866885,0.0001608773,0.0002506906,0.0001536421,0.00006697027,0.0001452146,0.0008811909,0.000162187,0.00001284255],"category_scores_gemma":[0.00001558141,0.0001531387,0.0001124365,0.0003317339,0.00004094923,0.0002925452,0.001201413,0.0006081409,0.000002312961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005365819,"about_ca_system_score_gemma":0.00005893952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000359454,"about_ca_topic_score_gemma":0.0001916047,"domain_scores_codex":[0.9986644,0.00007864503,0.0004046793,0.00044828,0.000186138,0.0002178014],"domain_scores_gemma":[0.9987934,0.00009996125,0.0001906778,0.0007935915,0.00007516171,0.00004721345],"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":[4.395761e-7,0.00005271224,0.01259666,0.00001730604,0.000004217091,8.489554e-7,0.00006873698,0.9400671,0.000005609028,0.0264106,0.00001791675,0.02075784],"study_design_scores_gemma":[0.00006342789,0.000005152054,0.2017037,0.00001699293,0.000003147559,0.000004496697,0.000008920655,0.7806396,0.000004011547,0.01742002,0.000006046872,0.0001244618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05163191,0.0001534885,0.9451089,0.001100007,0.0004429123,0.0002955295,0.00000328803,0.00008011195,0.001183857],"genre_scores_gemma":[0.789946,0.000002257864,0.209829,0.00006829366,0.00006008057,0.00002345169,0.00003815603,0.000005666531,0.00002714041],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7383141,"threshold_uncertainty_score":0.6244815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04659981070802097,"score_gpt":0.3181682499864549,"score_spread":0.2715684392784339,"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."}}