{"id":"W4387019753","doi":"10.3390/electronics12194027","title":"Efficient Hyperbolic Perceptron for Image Classification","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Perceptron; Convolutional neural network; Pattern recognition (psychology); Feature vector; Multilayer perceptron; Feature (linguistics); Flexibility (engineering); Euclidean geometry; Hyperbolic space; Euclidean space; Mathematics; Geometry","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":[0.0008716871,0.0008683048,0.0007664359,0.0005632594,0.0002648245,0.0008643735,0.001573568,0.0009468014,0.006091421],"category_scores_gemma":[0.001833336,0.0004334203,0.0006388406,0.000952817,0.0005720175,0.001687772,0.001149425,0.001742246,0.003481324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008346277,"about_ca_system_score_gemma":0.0008423883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002417947,"about_ca_topic_score_gemma":0.003262439,"domain_scores_codex":[0.9994828,0.0001086361,0.00003890555,0.0001406829,0.0001748258,0.00005411255],"domain_scores_gemma":[0.999613,0.0001140831,0.0000357881,0.0001072442,0.000105504,0.00002453659],"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":[0.0003095632,0.000116019,0.0008762931,0.0002747874,0.0001169132,0.0001457539,0.00007664974,0.2545931,0.01721077,0.04765308,0.01936169,0.6592654],"study_design_scores_gemma":[0.00000773848,0.00002437827,0.000122499,0.000008421209,0.000007211819,0.00003125727,0.000006573096,0.9839559,0.002698426,0.01080048,0.002329279,0.000007758055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01062826,0.001277406,0.9808195,0.0003438577,0.0001233136,0.0000442251,0.0002268485,0.002907969,0.003628696],"genre_scores_gemma":[0.4255213,0.001669803,0.542321,0.0006569863,0.0001990217,0.0002064639,0.001634554,0.0004180614,0.02737281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006091421,"threshold_uncertainty_score":0.02037781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02260086408657488,"score_gpt":0.2809664645143053,"score_spread":0.2583656004277305,"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."}}