{"id":"W2997837663","doi":"10.1609/aaai.v34i04.5852","title":"An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Generative grammar; Computer science; Artificial neural network; Artificial intelligence; Generative model; Set (abstract data type); Sampling (signal processing); Generative adversarial network; Image (mathematics); Mechanism (biology); Perspective (graphical); Adversarial system; Homogeneous; Pattern recognition (psychology); Scheme (mathematics); Machine learning; Computer vision; Mathematics","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":[0.001339601,0.0006216511,0.000800973,0.0005010952,0.0004724584,0.0006677512,0.001062091,0.0009628036,0.001052615],"category_scores_gemma":[0.004064944,0.0005480713,0.0006945076,0.0003489772,0.001305674,0.001147479,0.001856632,0.001174742,0.0002126632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007848514,"about_ca_system_score_gemma":0.0007051999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001697164,"about_ca_topic_score_gemma":0.001679786,"domain_scores_codex":[0.9995916,0.0001410173,0.00001673245,0.0000980583,0.0001005241,0.00005207554],"domain_scores_gemma":[0.9985863,0.0009282467,0.000116891,0.0001700234,0.0001203167,0.00007819103],"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":[0.0001614505,0.00003616265,0.001478529,0.00006058386,0.00003370299,0.0001864156,0.0002198946,0.8842459,0.01229208,0.033663,0.0009728745,0.06664938],"study_design_scores_gemma":[0.000004783896,0.00001229271,0.00005101888,0.000003818422,0.000003125899,0.00002476383,0.00000557575,0.993057,0.001339316,0.005289555,0.000205068,0.000003599013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02182556,0.0001170906,0.9768755,0.0000909857,0.00001129256,0.00002980768,0.00001444052,0.0002112469,0.0008239812],"genre_scores_gemma":[0.699397,0.0001725708,0.2973959,0.0002051715,0.00003546758,0.0001469925,0.0001277332,0.0001682578,0.002350937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001697164,"threshold_uncertainty_score":0.007084548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1079284681546799,"score_gpt":0.292621238046231,"score_spread":0.1846927698915511,"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."}}