{"id":"W2556967412","doi":"10.48550/arxiv.1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":806,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Receptive field; Computer science; Artificial intelligence; Convolutional neural network; Field (mathematics); Surround suppression; Gaussian; Dropout (neural networks); Computer vision; Pattern recognition (psychology); Machine learning; Mathematics; Visual perception; Psychology; Perception","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":[0.001712074,0.000494361,0.0005372541,0.0009291685,0.0003258373,0.001244936,0.0009973372,0.0009796703,0.001261005],"category_scores_gemma":[0.008218573,0.000514827,0.0003987314,0.0005866413,0.00214303,0.004698361,0.0009880287,0.001401724,0.0002559815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000972738,"about_ca_system_score_gemma":0.0006315792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001337616,"about_ca_topic_score_gemma":0.0008095299,"domain_scores_codex":[0.999576,0.0001415356,0.00002054919,0.00006915847,0.0001169676,0.00007581013],"domain_scores_gemma":[0.9963731,0.00269123,0.000242649,0.0002134845,0.000308409,0.0001710133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005921078,0.00003354034,0.001237236,0.000215893,0.00003142184,0.0001605971,0.0002114884,0.160684,0.01246625,0.800311,0.001937601,0.02265173],"study_design_scores_gemma":[0.00001111408,0.00002663175,0.0006145091,0.00004044362,0.000008575729,0.00008344983,0.00003358084,0.4452919,0.002221002,0.5498975,0.001754053,0.00001726531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07158436,0.003545004,0.9143935,0.001767474,0.00009576703,0.00002538276,0.000154306,0.0002366965,0.008197442],"genre_scores_gemma":[0.9302304,0.002436368,0.06318775,0.0003014021,0.0002589338,0.00007023956,0.000121764,0.000142085,0.003251005],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001712074,"threshold_uncertainty_score":0.009054422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09902396535453362,"score_gpt":0.1995139825676963,"score_spread":0.1004900172131627,"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."}}