{"id":"W2163605009","doi":"10.1145/3065386","title":"ImageNet classification with deep convolutional neural networks","year":2017,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":75709,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Softmax function; Convolutional neural network; Computer science; Pooling; Dropout (neural networks); Artificial intelligence; Convolution (computer science); Regularization (linguistics); Pattern recognition (psychology); Deep neural networks; Word error rate; Normalization (sociology); Artificial neural network; Machine learning","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":[0.002145549,0.004291728,0.001745342,0.004923501,0.0009539733,0.002239623,0.003369334,0.002578243,0.008449165],"category_scores_gemma":[0.004415059,0.0009643233,0.002167589,0.003795422,0.0006189827,0.002982893,0.002049554,0.002978047,0.008368459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00234163,"about_ca_system_score_gemma":0.001927261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0249474,"about_ca_topic_score_gemma":0.03049402,"domain_scores_codex":[0.9981959,0.0002005369,0.0001460544,0.0005872983,0.0004658035,0.0004044177],"domain_scores_gemma":[0.9988,0.0002140047,0.00009740301,0.0003265439,0.0004657339,0.00009623996],"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":[0.0006899321,0.0009756548,0.004618003,0.0007433288,0.0003890419,0.0004031077,0.0001061336,0.1663046,0.01387111,0.007953575,0.1860154,0.6179301],"study_design_scores_gemma":[0.0001138157,0.0002423204,0.002031687,0.00008895887,0.00006402336,0.0001304282,0.00005849564,0.9493261,0.01689397,0.007317997,0.02368286,0.00004949796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3012802,0.01260208,0.4536445,0.003058201,0.005960277,0.00228682,0.03712285,0.1300687,0.05397635],"genre_scores_gemma":[0.5015905,0.002430804,0.3542556,0.001560628,0.0008627268,0.001204723,0.1009214,0.001965996,0.03520772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0249474,"threshold_uncertainty_score":0.04960442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06443397073163805,"score_gpt":0.3127342939106008,"score_spread":0.2483003231789628,"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."}}