{"id":"W2809652586","doi":"10.1109/access.2018.2848307","title":"WPNets and PWNets: From the Perspective of Channel Fusion","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Taishan Scholar Project of Shandong Province; Natural Science Foundation of Shandong Province; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Computer science; Convolution (computer science); Channel (broadcasting); Benchmark (surveying); Network architecture; Artificial neural network; Code (set theory); Perspective (graphical); Architecture; Artificial intelligence; Data mining; Theoretical computer science; Computer network; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001141413,0.001317456,0.0008710129,0.0007169408,0.0004020256,0.001702172,0.001879153,0.001353243,0.002860168],"category_scores_gemma":[0.002775532,0.0004656723,0.0005527986,0.0007669959,0.00130412,0.006207366,0.002037954,0.002118357,0.0007216515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009202439,"about_ca_system_score_gemma":0.001066028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002500185,"about_ca_topic_score_gemma":0.002979317,"domain_scores_codex":[0.9995437,0.0001003148,0.00002251479,0.0001412352,0.0001109194,0.0000812634],"domain_scores_gemma":[0.9993308,0.0002018813,0.00007811989,0.0001959068,0.0001403438,0.0000529911],"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":[0.0006385653,0.0001845396,0.001991615,0.000326647,0.0002607023,0.0001819125,0.0001482049,0.5528303,0.01835306,0.1501554,0.01112572,0.2638032],"study_design_scores_gemma":[0.00001906616,0.0000873864,0.0003758893,0.00001916639,0.0000521611,0.00008582951,0.00002563392,0.9205303,0.006616935,0.06921373,0.002951335,0.000022682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0408616,0.001686624,0.9412259,0.0009589484,0.0002613436,0.00008144906,0.0004263501,0.00202581,0.01247197],"genre_scores_gemma":[0.7794509,0.001786827,0.2076631,0.0006890404,0.0003151854,0.0002288228,0.0008973173,0.0003003754,0.008668501],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002860168,"threshold_uncertainty_score":0.009568155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03608005885901672,"score_gpt":0.3237392153216412,"score_spread":0.2876591564626245,"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."}}