{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001117629,0.001254858,0.0006945695,0.000686421,0.0004931705,0.0006807457,0.003575515,0.000770867,0.003392333],"category_scores_gemma":[0.004835923,0.0005088852,0.0004881562,0.0006281524,0.0005856223,0.002570039,0.002009007,0.001282194,0.001081444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007416595,"about_ca_system_score_gemma":0.001416439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00330995,"about_ca_topic_score_gemma":0.006035842,"domain_scores_codex":[0.9995023,0.00006227975,0.00005634373,0.0001331481,0.0001623598,0.00008355924],"domain_scores_gemma":[0.9980939,0.0004513001,0.0001713979,0.0008896506,0.0003095492,0.00008407117],"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":[0.001397365,0.0005842984,0.006578124,0.00068013,0.0002067108,0.0006462772,0.0001915845,0.1716377,0.0464292,0.004859516,0.02814714,0.7386419],"study_design_scores_gemma":[0.0001695059,0.0006066213,0.00197829,0.00005412734,0.00007716507,0.000511535,0.0001037608,0.9055518,0.0773532,0.004179303,0.009358219,0.00005649561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3868617,0.005332049,0.5434478,0.0007801121,0.0009034006,0.0008390422,0.002495816,0.05135009,0.007990023],"genre_scores_gemma":[0.748403,0.0006981168,0.2372428,0.0006189921,0.00009053619,0.0004427635,0.00538283,0.0007649432,0.006355926],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003575515,"threshold_uncertainty_score":0.01134849,"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."}}