{"id":"W3124818821","doi":"10.48550/arxiv.2101.07528","title":"The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels\\n Methods","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Kernel (algebra); Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Feature extraction; Representation (politics); 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":[0.002268407,0.0009998002,0.0007766052,0.0004659098,0.0004592199,0.001195525,0.001456288,0.001296871,0.003230027],"category_scores_gemma":[0.01145603,0.0005767772,0.0005959992,0.0006193066,0.001796616,0.004064687,0.002062107,0.002465741,0.002160787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000708861,"about_ca_system_score_gemma":0.000534337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002510279,"about_ca_topic_score_gemma":0.004060058,"domain_scores_codex":[0.9984002,0.0003991761,0.00008218114,0.0004931849,0.0004924851,0.0001328389],"domain_scores_gemma":[0.9951926,0.002423578,0.000179047,0.001743481,0.0003590343,0.0001022441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008861837,0.0002063722,0.004159969,0.0009096243,0.0002981971,0.0001633088,0.0003181754,0.1165059,0.0375433,0.108881,0.01466765,0.7154604],"study_design_scores_gemma":[0.00009873026,0.0004544005,0.002623459,0.0001176587,0.00007462301,0.0005460965,0.0001196187,0.8354347,0.04095478,0.1025686,0.01695553,0.00005180271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1097992,0.005637866,0.8674787,0.001860942,0.0003895184,0.0001115562,0.0003360601,0.002961054,0.01142506],"genre_scores_gemma":[0.7052823,0.003030157,0.2797476,0.0007376084,0.0002596617,0.0001276155,0.0007505646,0.0007589761,0.009305527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003230027,"threshold_uncertainty_score":0.01199663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06143092665756005,"score_gpt":0.2423320159858164,"score_spread":0.1809010893282564,"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."}}