{"id":"W4312714398","doi":"10.1109/pn56061.2022.9908395","title":"In situ training with silicon photonics neural networks","year":2022,"lang":"en","type":"article","venue":"2022 Photonics North (PN)","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Queen's University","funders":"","keywords":"Photonics; Silicon photonics; Artificial neural network; Computer science; Electronics; Computer architecture; Silicon; Deep learning; Training (meteorology); Electronic engineering; Artificial intelligence; Engineering; Electrical engineering; Materials science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003604764,0.000342361,0.0002859792,0.0001584249,0.0003212898,0.0006365736,0.0009119049,0.0005792771,0.004968549],"category_scores_gemma":[0.001202854,0.0003085569,0.0001967077,0.0003050434,0.0004648471,0.001194058,0.0008464741,0.0009752631,0.0008121844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005102316,"about_ca_system_score_gemma":0.0007667423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001243346,"about_ca_topic_score_gemma":0.002504808,"domain_scores_codex":[0.9998071,0.00003375389,0.000007392908,0.00003791406,0.00007488836,0.00003908055],"domain_scores_gemma":[0.999697,0.0001554656,0.00002975328,0.00005438326,0.00004616861,0.00001726965],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005856461,0.000387681,0.002789189,0.000336712,0.0001495026,0.000329807,0.000228136,0.483836,0.1739466,0.06736149,0.01063092,0.2594182],"study_design_scores_gemma":[0.00001567055,0.00009609705,0.0002093118,0.00001402635,0.000009331806,0.00004164912,0.00002245709,0.9428568,0.04661666,0.006473179,0.003636395,0.000008421841],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.169695,0.0006490208,0.7957391,0.0008856921,0.0003622496,0.00007139137,0.0001947802,0.00295117,0.0294516],"genre_scores_gemma":[0.8500445,0.0003023115,0.1407291,0.0002026758,0.00004732355,0.00006238029,0.0001923018,0.0001308049,0.008288574],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004968549,"threshold_uncertainty_score":0.01662147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01421690319247848,"score_gpt":0.2163697239115324,"score_spread":0.2021528207190539,"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."}}