{"id":"W3105950517","doi":"","title":"Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hessian matrix; Stochastic gradient descent; Eigenvalues and eigenvectors; Computer science; Context (archaeology); Artificial intelligence; Mathematical optimization; Gradient descent; Ridge; Machine learning; Artificial neural network; Algorithm; Mathematics; Applied mathematics; Geology","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":[0.002809615,0.001784565,0.002011888,0.001218724,0.0008970217,0.001335501,0.00189738,0.002279301,0.005145236],"category_scores_gemma":[0.008420172,0.001056292,0.001202113,0.0007516684,0.001944605,0.002208625,0.00274696,0.002463736,0.001932561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005943329,"about_ca_system_score_gemma":0.001562413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002056328,"about_ca_topic_score_gemma":0.003150048,"domain_scores_codex":[0.9991992,0.0002968807,0.00004363046,0.0001585785,0.0002184458,0.00008324626],"domain_scores_gemma":[0.9974908,0.001520403,0.000200429,0.0003418418,0.0002929236,0.0001536498],"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":[0.0002590331,0.0002855121,0.00316761,0.0004151303,0.0002132322,0.0003662815,0.0004921448,0.6263403,0.01274184,0.1053658,0.01534792,0.2350052],"study_design_scores_gemma":[0.00004824255,0.00009660336,0.0001240495,0.00003453511,0.00001560416,0.0000893297,0.00004989722,0.9613045,0.00163981,0.0340962,0.0024795,0.00002170666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01277571,0.0002119349,0.9835081,0.0002503066,0.00005068882,0.00005345394,0.00003415334,0.0006453624,0.002470359],"genre_scores_gemma":[0.1908709,0.0002893409,0.8001939,0.0006115679,0.00007239897,0.0003120534,0.0002506705,0.000982478,0.00641666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005145236,"threshold_uncertainty_score":0.01721251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09298876824310644,"score_gpt":0.1914379755067182,"score_spread":0.0984492072636118,"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."}}