{"id":"W2963341152","doi":"10.1007/978-3-030-11018-5_37","title":"Adversarial network compression","year":2019,"lang":"en","type":"book-chapter","venue":"IRIS Research product catalog (Sapienza University of Rome)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Bundesministerium für Wirtschaft und Energie; Ministerio de Economía y Competitividad; Canadian Institute for Advanced Research","keywords":"Discriminator; Computer science; Adversarial system; Regularization (linguistics); Artificial intelligence; Artificial neural network; Deep neural networks; Compression (physics); Scheme (mathematics); Machine learning; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009965297,0.0002769173,0.0004718488,0.0005112079,0.0005951539,0.00006147733,0.002726898,0.0003396853,0.0002981166],"category_scores_gemma":[0.00003453021,0.0003145364,0.0002279847,0.0003724548,0.0005631949,0.0004187626,0.002207723,0.001124667,0.0007758433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002448974,"about_ca_system_score_gemma":0.0005626979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003491151,"about_ca_topic_score_gemma":0.00003846155,"domain_scores_codex":[0.9969687,0.0001121076,0.0002742802,0.001089289,0.001013843,0.0005417785],"domain_scores_gemma":[0.9964648,0.0001671554,0.000317619,0.002055879,0.0008032467,0.000191334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000137717,0.0001470886,0.00004484954,0.00022941,0.000192228,0.0000786235,0.0006614284,0.0002688498,0.001032553,0.4405886,0.4974009,0.05921772],"study_design_scores_gemma":[0.0003009184,0.0002342542,0.0001387141,0.0001775064,0.00001514604,0.00001263807,0.00002552969,0.0004309991,0.0004060257,0.01238593,0.9855357,0.0003365883],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0003388816,0.002085601,0.2813283,0.003011934,0.0009964501,0.004038868,0.0002689558,0.0009075619,0.7070235],"genre_scores_gemma":[0.02391163,0.001299595,0.03014724,0.0000453272,0.0007142513,0.000003159682,0.0002457734,0.00006888549,0.9435641],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4881349,"threshold_uncertainty_score":0.9999307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0441552592918066,"score_gpt":0.2908001374468965,"score_spread":0.2466448781550899,"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."}}