{"id":"W3103836948","doi":"10.1109/ipc47351.2020.9252216","title":"Photonic Long-Short Term Memory Neural Networks with Analog Memory","year":2020,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Photonics; Bandwidth (computing); Artificial neural network; Component (thermodynamics); Semiconductor memory; Electronic engineering; Computer architecture; Computer hardware; Engineering; Materials science; Computer network; Artificial intelligence; Optoelectronics; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001463368,0.0002830551,0.0003091113,0.00004801928,0.0002236311,0.0002923488,0.001429046,0.00008098501,0.00005174233],"category_scores_gemma":[0.000006732097,0.0001936462,0.0001200904,0.0007451645,0.00007766223,0.0004347813,0.0007242243,0.0004557224,0.00001700887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002168927,"about_ca_system_score_gemma":0.00004450052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002113072,"about_ca_topic_score_gemma":0.00003975843,"domain_scores_codex":[0.9978791,0.00008099378,0.0002959434,0.0007381742,0.0003672839,0.0006385138],"domain_scores_gemma":[0.9987917,0.00008893378,0.00007366693,0.0006002276,0.00006573653,0.0003797379],"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":[0.00005837595,0.00007263761,0.0108746,0.00004527589,0.0000946508,0.001235077,0.0003641536,0.8821206,0.0003207611,0.0003959084,0.005417916,0.09900005],"study_design_scores_gemma":[0.000265431,0.00024892,0.003826216,0.00001934517,0.00001042389,0.00009240708,0.00002316575,0.994634,0.0004734992,0.00001184602,0.00007765235,0.0003171074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2246551,0.0005773516,0.7592416,0.004204493,0.0006156057,0.0004203703,3.9575e-7,0.0008441927,0.009440925],"genre_scores_gemma":[0.990003,0.0000181108,0.005353036,0.003759497,0.0005567118,0.000007407565,0.000003194024,0.00002356352,0.0002754512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7653479,"threshold_uncertainty_score":0.7896663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01791753916466465,"score_gpt":0.2245463589876188,"score_spread":0.2066288198229541,"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."}}