{"id":"W3196643773","doi":"10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00017","title":"CE-Dedup: Cost-Effective Convolutional Neural Nets Training based on Image Deduplication","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Data deduplication; Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Hash function; Image (mathematics); Computation; Data mining; Machine learning; Database; Algorithm","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":[0.0001091218,0.0001636768,0.0001433733,0.00006290228,0.0002317527,0.0001014607,0.0004291838,0.00005162529,0.00008882041],"category_scores_gemma":[0.00008515415,0.0001635212,0.00007815691,0.0006835039,0.00006862463,0.0004149663,0.000112856,0.000198892,0.0001368183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091252,"about_ca_system_score_gemma":0.0001296738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003017537,"about_ca_topic_score_gemma":0.000007203688,"domain_scores_codex":[0.9984761,0.0001042753,0.0002002251,0.0006275289,0.000266678,0.0003251452],"domain_scores_gemma":[0.9983176,0.0005949548,0.00008659253,0.0006594066,0.0002053425,0.0001361196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002855749,0.000339637,0.0002691449,0.00001059342,0.00002049869,0.00004208739,0.000270698,0.08067384,0.03579543,0.388281,0.006862068,0.4874065],"study_design_scores_gemma":[0.000446506,0.00005411261,0.008142249,0.00001003779,0.000004479553,0.00002889324,0.00002396887,0.9645663,0.01259154,0.004865926,0.009051626,0.0002143731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002737307,0.00003570587,0.9788331,0.007092094,0.0001644764,0.0008144391,0.000006378449,0.0003636244,0.009952877],"genre_scores_gemma":[0.8403209,0.000003056262,0.1519018,0.006451047,0.0001050125,0.0008575382,0.00005096356,0.00001582694,0.0002938203],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8838925,"threshold_uncertainty_score":0.6668202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03126829301571458,"score_gpt":0.2960097585946011,"score_spread":0.2647414655788865,"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."}}