{"id":"W3101581426","doi":"","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Artificial neural network; Kernel (algebra); Chaotic; Artificial intelligence; Tangent; Computer science; Linearization; Deep learning; Nonlinear system; Machine learning; Geometry; Algorithm; Mathematics; Physics; Discrete 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":[0.003138174,0.0005004883,0.0004382275,0.00118366,0.0003719577,0.001157606,0.0006113508,0.0009310854,0.001155895],"category_scores_gemma":[0.02928485,0.0002965961,0.0004186081,0.0008601443,0.002200197,0.003832416,0.001225783,0.001728585,0.0001909761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0010928,"about_ca_system_score_gemma":0.0003615326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001937082,"about_ca_topic_score_gemma":0.00124196,"domain_scores_codex":[0.9992937,0.0002709639,0.00004165675,0.0001727104,0.0001499861,0.00007095275],"domain_scores_gemma":[0.9865067,0.00929375,0.001806517,0.001247124,0.0007333629,0.0004125418],"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":[0.001105442,0.0003792952,0.1600295,0.0006058439,0.0003509612,0.0006687836,0.002199427,0.6032231,0.01539696,0.08535464,0.006591543,0.1240944],"study_design_scores_gemma":[0.00002273207,0.000290608,0.06836916,0.00008472741,0.00003134209,0.0004188756,0.0003943602,0.899161,0.004145933,0.02511492,0.001896584,0.0000697061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9128288,0.001773409,0.08034497,0.0008689053,0.00004157743,0.00005881003,0.0004400165,0.0003040047,0.003339454],"genre_scores_gemma":[0.9945759,0.0002225176,0.004406659,0.00003590618,0.00001917895,0.00002049506,0.0002898199,0.00006612683,0.0003634251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003138174,"threshold_uncertainty_score":0.01659644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02115437571371863,"score_gpt":0.263866539708851,"score_spread":0.2427121639951324,"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."}}