{"id":"W4399332322","doi":"10.1016/j.neunet.2024.106420","title":"Capacity bounds for hyperbolic neural network representations of latent tree structures","year":2024,"lang":"en","type":"article","venue":"Neural Networks","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Embedding; Mathematics; Representation (politics); Tree (set theory); Distortion (music); Euclidean space; Curvature; Dimension (graph theory); Artificial neural network; Upper and lower bounds; Activation function; Hyperbolic tree; Function (biology); Graph; Perceptron; Euclidean geometry; Discrete mathematics; Algorithm; Combinatorics; Computer science; Hyperbolic geometry; Pure mathematics; Artificial intelligence; Differential geometry; Mathematical analysis; Geometry","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":[],"consensus_categories":[],"category_scores_codex":[0.0001774521,0.0001604055,0.0002777175,0.000135531,0.0001567537,0.0002425974,0.0007184066,0.00009614359,0.00003435226],"category_scores_gemma":[0.00006245614,0.000116278,0.0002696544,0.001820522,0.0001057457,0.0003352214,0.000228315,0.0002172892,0.000002457863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001551737,"about_ca_system_score_gemma":0.00001271024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001043849,"about_ca_topic_score_gemma":0.00006090707,"domain_scores_codex":[0.9984814,0.00007116905,0.0003403987,0.0004802385,0.0002176116,0.0004091715],"domain_scores_gemma":[0.9987961,0.0004582923,0.00007834143,0.0004943179,0.0000658421,0.0001071151],"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":[0.00001868195,0.0000399071,0.004629708,0.00003039497,0.0001425063,0.00002129348,0.00009253134,0.5821036,0.00005039012,0.1136443,0.02168476,0.277542],"study_design_scores_gemma":[0.0001129941,0.0001035589,0.02352208,0.000006536069,0.00004953391,0.00001497705,0.000002750333,0.9551882,0.00002258587,0.01804114,0.002804502,0.000131159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2215915,0.005618435,0.7623491,0.004857298,0.003869944,0.0005014846,0.0000739708,0.0005431182,0.0005951194],"genre_scores_gemma":[0.9929335,0.00005006099,0.005772823,0.0003238052,0.0006417742,0.00002329961,0.00003882458,0.000008508139,0.0002074313],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.771342,"threshold_uncertainty_score":0.4741679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03486758422580956,"score_gpt":0.2775667507472389,"score_spread":0.2426991665214294,"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."}}