{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005226299,0.001566433,0.0006344114,0.0007504917,0.0004999748,0.001118164,0.002764649,0.0006706553,0.006303017],"category_scores_gemma":[0.001749734,0.0005324521,0.0007226521,0.0008509686,0.0006469626,0.002531765,0.001781049,0.001403985,0.001876525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001013984,"about_ca_system_score_gemma":0.001562997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005940191,"about_ca_topic_score_gemma":0.01543784,"domain_scores_codex":[0.9997107,0.00004193303,0.00001585619,0.0001057709,0.00007838164,0.00004732383],"domain_scores_gemma":[0.9995683,0.00009512148,0.00004103667,0.0001575066,0.0001025706,0.00003555359],"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":[0.0004086866,0.0002524145,0.001607791,0.0003604948,0.0002207174,0.0002389438,0.0001147688,0.4485453,0.02540761,0.03241323,0.06531703,0.425113],"study_design_scores_gemma":[0.00003669235,0.00007456855,0.0001670899,0.00001286552,0.00002797334,0.00005438782,0.00001991697,0.9721994,0.00865359,0.01008014,0.008656234,0.00001715667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03542254,0.0007732591,0.9292364,0.0006185961,0.0003107374,0.0001634153,0.0007900794,0.02014402,0.01254103],"genre_scores_gemma":[0.3983838,0.0007556592,0.576645,0.0006843734,0.0001710534,0.0004533298,0.005975371,0.002127401,0.01480405],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006303017,"threshold_uncertainty_score":0.02108568,"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."}}