{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00159926,0.001108341,0.0008532083,0.0005488989,0.0002869731,0.0007555492,0.001263783,0.001175147,0.002251106],"category_scores_gemma":[0.005346577,0.0004755113,0.0005717439,0.0004117293,0.0009275542,0.001287432,0.00168552,0.002327331,0.0010114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005641263,"about_ca_system_score_gemma":0.0005544606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001343413,"about_ca_topic_score_gemma":0.002112071,"domain_scores_codex":[0.9993287,0.0002874916,0.00002639546,0.000140927,0.0001509006,0.00006545436],"domain_scores_gemma":[0.9986168,0.0007948666,0.000116679,0.0002516639,0.0001602998,0.00005961681],"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":[0.0001082902,0.00009221716,0.001293421,0.00008395483,0.000067822,0.0001011189,0.000114045,0.8786754,0.01316721,0.02159868,0.003880666,0.08081712],"study_design_scores_gemma":[0.000003425078,0.00001175709,0.00006621915,0.000004995393,0.000002761371,0.00001762541,0.000002792052,0.9942836,0.001289518,0.003938985,0.0003749047,0.000003430597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01354468,0.0002722064,0.9828193,0.000220302,0.0000402011,0.00002404866,0.0000515655,0.00105806,0.001969688],"genre_scores_gemma":[0.7205126,0.0004052947,0.2699108,0.0006481867,0.0001034363,0.0001602081,0.0005193204,0.0006524879,0.007087635],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002251106,"threshold_uncertainty_score":0.008457839,"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."}}