{"id":"W4392026366","doi":"10.1109/cleo-pr62338.2022.10432530","title":"Silicon Photonics for Training Deep Neural Networks","year":2022,"lang":"en","type":"article","venue":"","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":"Training (meteorology); Photonics; Artificial neural network; Computer science; Silicon photonics; Silicon; Artificial intelligence; Optoelectronics; Materials science","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":[0.0003459901,0.0003143894,0.0001804978,0.000231217,0.0002514374,0.0008159629,0.0005825193,0.0006049746,0.009296885],"category_scores_gemma":[0.000937545,0.0002644112,0.0002107227,0.0003251781,0.0004441759,0.001013878,0.000563064,0.0009781776,0.002078726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005219195,"about_ca_system_score_gemma":0.0006709017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007477565,"about_ca_topic_score_gemma":0.001398526,"domain_scores_codex":[0.9997742,0.0000304844,0.000008813988,0.00004016327,0.0001191894,0.00002719994],"domain_scores_gemma":[0.9997625,0.0001036763,0.0000248364,0.00004036077,0.0000537077,0.00001491308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003434921,0.0002206377,0.00135209,0.0005237857,0.000132369,0.0002196758,0.000118127,0.09030256,0.1636136,0.3221261,0.03403961,0.387008],"study_design_scores_gemma":[0.00006403667,0.0002100006,0.0005160256,0.00007610238,0.0000349088,0.0001682055,0.00003061834,0.7841817,0.09203335,0.05870509,0.06394777,0.00003222525],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05077335,0.003512014,0.8729956,0.002316086,0.0009971209,0.00008323018,0.0003697762,0.003065202,0.06588773],"genre_scores_gemma":[0.655925,0.002752992,0.3083225,0.0008797782,0.0002839299,0.0001459649,0.0005358843,0.0003271415,0.03082689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009296885,"threshold_uncertainty_score":0.03110123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0285258005363965,"score_gpt":0.244532524395024,"score_spread":0.2160067238586275,"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."}}