{"id":"W4401977444","doi":"10.1088/2634-4386/ad5d0f","title":"Kernel heterogeneity improves sparseness of natural images representations","year":2024,"lang":"en","type":"article","venue":"Neuromorphic Computing and Engineering","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Agence Nationale de la Recherche","keywords":"Kernel (algebra); Artificial intelligence; Natural (archaeology); Computer science; Pattern recognition (psychology); Mathematics; Machine learning; Statistics; Geography; Archaeology; Combinatorics","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":[0.0001035235,0.0001091206,0.0001259208,0.0001138011,0.00005853107,0.0001436446,0.0001920386,0.00001640818,5.548386e-7],"category_scores_gemma":[0.00005284539,0.0001048069,0.00004396898,0.0002739276,0.0000251397,0.0002625449,0.0002309705,0.0001677586,0.000001703045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000706471,"about_ca_system_score_gemma":0.00001263743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000891696,"about_ca_topic_score_gemma":1.838813e-7,"domain_scores_codex":[0.999222,0.00001454253,0.0001753632,0.0003064101,0.0001136856,0.0001679481],"domain_scores_gemma":[0.9995115,0.0001677869,0.00002733291,0.0002126928,0.00002918583,0.0000514721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002802607,0.00002856694,0.0006290213,0.0004400422,0.00004235172,0.0001524526,0.0006700435,0.03254115,0.6443285,0.007665028,0.0001601696,0.3133399],"study_design_scores_gemma":[0.00007305767,0.00001454593,0.00952132,0.0001092728,0.000003850995,0.0001122495,0.000006650943,0.9750713,0.01462948,0.00008496564,0.0002700163,0.0001033357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3653454,0.001342205,0.6318024,0.0002080789,0.0008625915,0.00004458115,0.000001179765,0.0003484964,0.00004502753],"genre_scores_gemma":[0.9700062,0.00003211181,0.02984272,0.00003099227,0.00005486434,8.79626e-7,8.954771e-7,0.00001098154,0.00002039786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9425301,"threshold_uncertainty_score":0.42739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01679178309519349,"score_gpt":0.266122978775732,"score_spread":0.2493311956805385,"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."}}