{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006002734,0.0003720123,0.0004029367,0.0003900204,0.0001714754,0.0006227197,0.0006002514,0.0004987731,0.0009825189],"category_scores_gemma":[0.004147362,0.000189561,0.0002826982,0.0003008449,0.0007145549,0.001139492,0.001107264,0.0007371338,0.0001599606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005887735,"about_ca_system_score_gemma":0.0003953733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001039401,"about_ca_topic_score_gemma":0.0008310573,"domain_scores_codex":[0.9997153,0.00006022062,0.00001689644,0.00007567635,0.0000930071,0.00003890488],"domain_scores_gemma":[0.9985915,0.0006539591,0.0001955902,0.0003096618,0.0001637161,0.00008557238],"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":[0.0004643592,0.0001552503,0.003274473,0.0001721421,0.00008187865,0.000244758,0.0001552238,0.7191257,0.1548242,0.04277203,0.00139219,0.07733788],"study_design_scores_gemma":[0.000008325713,0.00006113636,0.0006349708,0.000004822961,0.000008324037,0.00006425129,0.00001432653,0.9747629,0.015339,0.008720086,0.0003738795,0.000007949877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3761048,0.0001644489,0.6208841,0.0002790909,0.00002583194,0.00002338808,0.00009790295,0.0005652525,0.001855174],"genre_scores_gemma":[0.975935,0.00005951381,0.02313715,0.0000614481,0.00001259876,0.00001265254,0.00009188095,0.0000462243,0.000643622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001039401,"threshold_uncertainty_score":0.004271865,"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."}}