{"id":"W4385496436","doi":"10.20944/preprints202308.0070.v1","title":"Efficient Hyperbolic Perceptron for Image Classification","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Multilayer perceptron; Convolutional neural network; Feature vector; Euclidean geometry; Classifier (UML); Hyperbolic space; Feature (linguistics); Machine learning; 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":[0.0006958725,0.0007838809,0.0009610833,0.0005888742,0.0002742998,0.0009126554,0.001676529,0.00117046,0.005833444],"category_scores_gemma":[0.001668392,0.0004250876,0.0007516225,0.0009919617,0.000619409,0.0017061,0.001110391,0.001542358,0.002445848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001009775,"about_ca_system_score_gemma":0.0008723493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003679328,"about_ca_topic_score_gemma":0.004185554,"domain_scores_codex":[0.9995191,0.00008936845,0.00003811021,0.0001427366,0.0001413596,0.0000693171],"domain_scores_gemma":[0.9996742,0.0001034423,0.00003409692,0.00007499497,0.0000895083,0.00002382652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002784503,0.0001154832,0.0009404403,0.0002203638,0.00008842217,0.0001420703,0.00007741884,0.3595003,0.01244785,0.04238993,0.01289936,0.5708998],"study_design_scores_gemma":[0.000004005158,0.00001243278,0.00006746122,0.000004160609,0.000003859687,0.00001300138,0.000003762663,0.9914589,0.001046383,0.006472597,0.0009096388,0.00000370187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01364857,0.0009666434,0.9789185,0.0003478728,0.00009506878,0.00004784956,0.0002227526,0.002335008,0.003417658],"genre_scores_gemma":[0.5387605,0.001122112,0.4375358,0.0006310202,0.000156501,0.0002033881,0.00143202,0.0002821535,0.01987652],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005833444,"threshold_uncertainty_score":0.0195148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2995563504885592,"score_gpt":0.3900441209364108,"score_spread":0.09048777044785156,"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."}}