{"id":"W2786720420","doi":"10.48550/arxiv.1805.03644","title":"Improving GAN Training via Binarized Representation Entropy (BRE) Regularization","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Royal Bank of Canada","funders":"","keywords":"Discriminator; Computer science; Extrapolation; Cross entropy; Regularization (linguistics); Binary number; Entropy (arrow of time); Stability (learning theory); Artificial intelligence; Machine learning; Generative grammar; Generator (circuit theory); Representation (politics); Pattern recognition (psychology); Mathematics; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.0003595632,0.0003499699,0.0003844326,0.0002736825,0.0003486605,0.0003144682,0.001242765,0.0003009661,0.0000529128],"category_scores_gemma":[0.00008791497,0.0004067925,0.0002345081,0.000720677,0.0001406248,0.0008256239,0.001029518,0.0003596056,0.00004838833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000195296,"about_ca_system_score_gemma":0.0002010085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002374316,"about_ca_topic_score_gemma":0.00002212536,"domain_scores_codex":[0.9973622,0.0003793651,0.0002924911,0.001400217,0.0001440136,0.0004217025],"domain_scores_gemma":[0.9976905,0.00009942536,0.0005080649,0.00122048,0.0003240084,0.0001575356],"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":[0.0001375695,0.0001571221,0.0007050693,0.00008911201,0.000334238,0.0002638656,0.002526224,0.8990545,0.01821765,0.04650933,0.0007648242,0.03124046],"study_design_scores_gemma":[0.0005114061,0.00006063545,0.0002291019,0.00005407637,0.00008164893,0.00000374627,0.00008750152,0.9703249,0.003949268,0.02405735,0.0002179436,0.0004224729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01200611,0.00002205924,0.9845922,0.0001297848,0.001207261,0.0003677419,0.000005177878,0.0002581453,0.001411508],"genre_scores_gemma":[0.9617478,0.00003387469,0.03645829,0.00007826433,0.0004349547,0.000001748544,0.00004979716,0.00002576974,0.001169542],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9497417,"threshold_uncertainty_score":0.9998384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06697326294661823,"score_gpt":0.1937103355183944,"score_spread":0.1267370725717762,"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."}}