{"id":"W4360994195","doi":"10.1109/tc.2023.3236868","title":"Tensor Recurrent Neural Network With Differential Privacy","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"Science and Technology Program of Guizhou Province; National Natural Science Foundation of China","keywords":"Differential privacy; Recurrent neural network; Computer science; Deep learning; Artificial intelligence; Tensor (intrinsic definition); Machine learning; Artificial neural network; Data mining","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0001337417,0.0002918036,0.0002511382,0.000307119,0.0003470129,0.0002391132,0.01223727,0.0001055031,0.00001495273],"category_scores_gemma":[0.00005675564,0.0002488023,0.000112915,0.001582214,0.0001198709,0.0004716568,0.0008711928,0.0005232192,0.0001663493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008225233,"about_ca_system_score_gemma":0.00004269672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001192992,"about_ca_topic_score_gemma":0.000008006093,"domain_scores_codex":[0.997764,0.00008898682,0.0002671166,0.0007578065,0.0004563786,0.0006657249],"domain_scores_gemma":[0.9945964,0.0002755429,0.00008764963,0.004863019,0.00005339612,0.0001239877],"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":[0.0000927097,0.0002961257,0.000136348,0.00003701662,0.0002001326,0.0001658023,0.0002036678,0.1607985,0.0001487743,0.0003560169,0.2650058,0.5725591],"study_design_scores_gemma":[0.0006047466,0.0003609694,0.001034538,0.00009840231,0.00001762351,0.00003769441,0.000007184661,0.9930733,0.0009839281,0.002160682,0.001244505,0.0003764422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03718934,0.000008846132,0.9444128,0.01075189,0.003745649,0.000279773,0.00001781795,0.003558842,0.00003505805],"genre_scores_gemma":[0.840581,0.00004879737,0.1588011,0.0002753575,0.000128893,0.00006539759,0.000009500842,0.00003415515,0.00005579715],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8322748,"threshold_uncertainty_score":0.9999964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03349375374757956,"score_gpt":0.2605833325612889,"score_spread":0.2270895788137093,"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."}}