{"id":"W4387432194","doi":"10.48550/arxiv.2310.03212","title":"PDR-CapsNet: an Energy-Efficient Parallel Approach to Dynamic Routing in Capsule Networks","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Convolutional neural network; Overfitting; Adaptive routing; Energy consumption; Pooling; Routing (electronic design automation); Artificial intelligence; Efficient energy use; Throughput; Deep learning; FLOPS; Computational complexity theory; Parallel computing; Artificial neural network; Algorithm; Link-state routing protocol; Computer network; Routing protocol","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":[0.0003073863,0.0004430623,0.0004224517,0.0004381962,0.0002284728,0.0001341558,0.003002429,0.0003285732,0.000002348982],"category_scores_gemma":[0.00001763742,0.00054716,0.000151179,0.002295177,0.00009062463,0.0002618391,0.003276682,0.0007771309,0.00004454178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004620511,"about_ca_system_score_gemma":0.00009723469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004045469,"about_ca_topic_score_gemma":0.0004655624,"domain_scores_codex":[0.996363,0.0001929378,0.0003542993,0.002176981,0.0001322747,0.0007805196],"domain_scores_gemma":[0.9971312,0.00009010924,0.0002648742,0.002067417,0.00009028556,0.0003561517],"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":[0.000006060828,0.0001297303,0.0002109201,0.000007937747,0.00001306182,0.00005241311,0.0001676603,0.8589637,0.000008933032,0.139843,0.00005493061,0.0005416122],"study_design_scores_gemma":[0.0002394631,0.0000260123,0.00338407,0.00005226967,0.00001399736,0.000002332401,0.00007284373,0.9844402,0.000004005773,0.01116589,0.00004548691,0.0005533974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.100518,0.00002379187,0.8970429,0.00007434501,0.0003267499,0.0005232265,0.000007497686,0.0005898378,0.0008936792],"genre_scores_gemma":[0.9849246,0.00007402623,0.01355253,0.0001398903,0.00007951211,0.00002464168,0.00007576464,0.00005139188,0.00107767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8844066,"threshold_uncertainty_score":0.999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07348075076730022,"score_gpt":0.2101058959340185,"score_spread":0.1366251451667183,"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."}}