{"id":"W2902205493","doi":"10.1088/1757-899x/450/5/052004","title":"An approach for automating the design of convolutional neural networks","year":2018,"lang":"en","type":"article","venue":"IOP Conference Series Materials Science and Engineering","topic":"Advanced Computational Techniques in Science and Engineering","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Education and Science of the Russian Federation; Canadian Institute for Advanced Research","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Artificial neural network; Deep learning; Contextual image classification; Field (mathematics); Pattern recognition (psychology); Process (computing); Image (mathematics); Machine learning; Neocognitron; Time delay neural network; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001323589,0.0001388175,0.000157569,0.0001012283,0.0003662697,0.0003567785,0.001093396,0.00003664601,0.000002366684],"category_scores_gemma":[0.000144014,0.0001056639,0.00001440277,0.0005117283,0.0006338015,0.001906801,0.000185199,0.00005299784,2.137293e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002579874,"about_ca_system_score_gemma":0.0001016437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003848578,"about_ca_topic_score_gemma":9.661466e-8,"domain_scores_codex":[0.998728,0.00001829871,0.0002472226,0.0003402141,0.0003071669,0.0003591454],"domain_scores_gemma":[0.9990129,0.00008785071,0.00008482463,0.0003032796,0.0004357264,0.00007541174],"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":[0.000006769124,0.000006832698,0.000003013309,0.00002106926,0.000002523297,2.385761e-7,0.000381386,0.4637691,0.3940807,0.1381286,0.000004704739,0.003595071],"study_design_scores_gemma":[0.00005044045,0.0001465199,0.0002755189,0.0000144163,0.000001822498,0.000025503,0.00004934572,0.9041101,0.0938442,0.001338566,0.00001807663,0.0001254444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04100496,0.0000190588,0.9580926,0.00006165535,0.0003805531,0.0002206951,0.000002554521,0.0001832285,0.00003465196],"genre_scores_gemma":[0.6240073,0.000004093383,0.3758323,0.00002662476,0.00008374856,0.00003861284,9.728567e-7,0.000004337506,0.000001966602],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5830024,"threshold_uncertainty_score":0.4308847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02990260170755966,"score_gpt":0.2607367763251426,"score_spread":0.230834174617583,"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."}}