{"id":"W2106662462","doi":"","title":"Convex Deep Learning via Normalized Kernels","year":2014,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Deep learning; Computer science; Heuristics; Parametric statistics; Range (aeronautics); Artificial intelligence; Regular polygon; Nonparametric statistics; Machine learning; Layer (electronics); Kernel (algebra); Mathematical optimization; Mathematics; Engineering","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":[0.0008837483,0.0007954313,0.0004582673,0.0003784407,0.000201446,0.0007007939,0.0007583477,0.0005678783,0.001560804],"category_scores_gemma":[0.004269637,0.0004275748,0.0003571318,0.0003996527,0.001417046,0.002270552,0.001555793,0.001661556,0.0004287266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000957531,"about_ca_system_score_gemma":0.0007561759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002252444,"about_ca_topic_score_gemma":0.002781525,"domain_scores_codex":[0.9994692,0.0002001014,0.00002328672,0.00008617144,0.0001786175,0.00004263673],"domain_scores_gemma":[0.9991566,0.00039391,0.0000972484,0.0001749894,0.0001303563,0.00004696212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005113593,0.0000170732,0.0002657773,0.00005937339,0.00002162834,0.00004871316,0.00005488566,0.7135185,0.006164561,0.2375372,0.001415401,0.04084561],"study_design_scores_gemma":[0.000001501775,0.000006402193,0.00003396046,0.000003264383,0.000001043255,0.000007850439,0.000003225307,0.9665998,0.0007012626,0.03219302,0.0004459182,0.000002674914],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007554144,0.0001001896,0.9906728,0.0001294087,0.000009810727,0.000007980843,0.00003461282,0.0001070111,0.001384045],"genre_scores_gemma":[0.6286927,0.0009358005,0.3617966,0.0001966855,0.00008886175,0.0001411409,0.0003111017,0.0002072756,0.007629705],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002252444,"threshold_uncertainty_score":0.006947398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007515000331167515,"score_gpt":0.2033569785074465,"score_spread":0.195841978176279,"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."}}