{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008745025,0.0004163901,0.0003890813,0.0003239123,0.0003502771,0.0000902124,0.0009108487,0.0003900892,0.0004019569],"category_scores_gemma":[0.002397928,0.0004496306,0.0003674002,0.0003573415,0.0002297173,0.00005897679,0.0008168453,0.0008449553,0.008019326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003622956,"about_ca_system_score_gemma":0.0001703583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003088412,"about_ca_topic_score_gemma":0.000006068972,"domain_scores_codex":[0.9959929,0.00028604,0.000670376,0.002003508,0.0005271907,0.000519992],"domain_scores_gemma":[0.9970484,0.0003536576,0.0005003565,0.001739009,0.0001793502,0.0001791635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006720402,0.000196706,0.002256435,0.0001994784,0.00001167818,0.000003074691,0.0005774174,0.001052978,0.9919547,0.002244505,0.0002829994,0.001152783],"study_design_scores_gemma":[0.0006504863,0.00003370962,0.4035059,0.0001102478,0.00007198078,0.00001802855,0.000365145,0.07794128,0.5032893,0.003042826,0.01020249,0.0007685673],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9791526,0.000009284264,0.004838581,0.003208259,0.002527305,0.002207136,0.0001130786,0.001345536,0.006598189],"genre_scores_gemma":[0.9896077,0.00006059253,0.000262589,0.0003133738,0.0003875246,0.001865609,0.00006545062,0.0001279194,0.007309233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4886654,"threshold_uncertainty_score":0.9997956,"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."}}