{"id":"W3127178140","doi":"10.1109/aiccsa50499.2020.9316525","title":"Quick-CapsNet (QCN): A Fast Alternative to Capsule Networks","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MNIST database; Computer science; Convolutional neural network; Robustness (evolution); Bottleneck; Artificial intelligence; Inference; Affine transformation; Pattern recognition (psychology); Deep learning; Embedded system; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001077615,0.0004731826,0.0004783695,0.0001104955,0.0001451238,0.0003027191,0.003637603,0.0002002371,0.00003961053],"category_scores_gemma":[0.00003585029,0.0004637826,0.0001634757,0.0007353767,0.00005026427,0.0002114015,0.006969298,0.0009922804,0.0005629544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001448814,"about_ca_system_score_gemma":0.0001116368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001219152,"about_ca_topic_score_gemma":0.00004306616,"domain_scores_codex":[0.9967886,0.00008277925,0.0004742203,0.001658476,0.0004107453,0.0005851552],"domain_scores_gemma":[0.9971532,0.0001036868,0.0002516854,0.001813251,0.00015616,0.000521982],"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":[0.000008748256,0.00007353193,0.00002058928,0.0000252448,0.00008149582,0.00004324113,0.001066428,0.745154,0.0002476685,0.1528749,0.05638411,0.04402002],"study_design_scores_gemma":[0.0001674953,0.00007284989,0.0002170098,0.00005654958,0.00001277271,0.000009027279,0.00001873412,0.9376525,0.0007777038,0.04344207,0.01685891,0.0007143504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003789286,0.000131217,0.9757248,0.01290131,0.001037142,0.001167472,0.00002087997,0.0008219707,0.007816275],"genre_scores_gemma":[0.4720935,0.0001375334,0.5108744,0.01224608,0.001708396,0.0009892969,0.00007956052,0.00008205145,0.001789229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4717146,"threshold_uncertainty_score":0.9997814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03345229799583384,"score_gpt":0.2931242798028724,"score_spread":0.2596719818070386,"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."}}