{"id":"W3038052564","doi":"10.1515/nanoph-2020-0171","title":"Boolean learning under noise‐perturbations in hardware neural networks","year":2018,"lang":"en","type":"article","venue":"Nanophotonics","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"H2020 Marie Skłodowska-Curie Actions; European Commission; Agence Nationale de la Recherche; Volkswagen Foundation; Ottawa Hospital Research Institute","keywords":"Artificial neural network; Computer science; Noise (video); Path (computing); Convergence (economics); Focus (optics); Artificial intelligence; Computer engineering; Computer network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008031757,0.0002678204,0.0005348015,0.0002952176,0.0002988079,0.0008630341,0.0007236421,0.0008168934,0.001320139],"category_scores_gemma":[0.004701448,0.0002409714,0.0002466212,0.0001736829,0.00150035,0.001218621,0.0007198855,0.0006963896,0.0001076093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001253442,"about_ca_system_score_gemma":0.0005636152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00168721,"about_ca_topic_score_gemma":0.001107508,"domain_scores_codex":[0.9995909,0.0001670555,0.00001539875,0.00005428252,0.0001061307,0.00006621109],"domain_scores_gemma":[0.9984889,0.001008643,0.0002126302,0.00007911738,0.0001283093,0.00008247251],"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":[0.0002038222,0.00006077552,0.0008282889,0.00009922025,0.00003200214,0.0002140913,0.00009173968,0.7561632,0.02394505,0.2090694,0.0005133545,0.008779026],"study_design_scores_gemma":[0.000007286029,0.00001876875,0.0001092175,0.000003183091,0.000002251195,0.00001147669,0.000006342153,0.9804356,0.001392731,0.01794287,0.00006497021,0.000005311999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7046673,0.0004250145,0.2816052,0.001397265,0.00008218564,0.00004067316,0.0001038893,0.0004049202,0.01127349],"genre_scores_gemma":[0.9944631,0.00005347317,0.004408528,0.00005301132,0.000009069911,0.0000189857,0.00001625914,0.00001642805,0.0009611234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00168721,"threshold_uncertainty_score":0.009094417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01377232049490312,"score_gpt":0.2406766571890348,"score_spread":0.2269043366941317,"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."}}