{"id":"W4366140936","doi":"10.1364/prj.484662","title":"Sophisticated deep learning with on-chip optical diffractive tensor processing","year":2023,"lang":"en","type":"article","venue":"Photonics Research","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Beijing Municipal Science and Technology Commission; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Convolutional neural network; Artificial intelligence; Computer engineering; Stochastic gradient descent; Computational science; Computer architecture; Pattern recognition (psychology); Electronic engineering; Artificial neural network; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0003250095,0.0006617025,0.0002738104,0.0003600487,0.0002776996,0.0005929976,0.001154074,0.0004682124,0.002242738],"category_scores_gemma":[0.0008217147,0.0002400397,0.000335189,0.0004831923,0.0004557484,0.001134847,0.0007605361,0.0007345025,0.0005317027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007918227,"about_ca_system_score_gemma":0.0008982063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003783157,"about_ca_topic_score_gemma":0.008362019,"domain_scores_codex":[0.9997877,0.00002781812,0.000008802968,0.00003757163,0.00009559776,0.00004251493],"domain_scores_gemma":[0.9998295,0.00003727867,0.00002605228,0.00004604865,0.0000455087,0.00001550253],"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":[0.000362505,0.0003448319,0.004081033,0.0003762743,0.0001827259,0.0002837635,0.0001625533,0.2960728,0.1487323,0.05529658,0.0115185,0.4825861],"study_design_scores_gemma":[0.00001379054,0.00007385017,0.0003386741,0.00001102187,0.00001663345,0.00005294157,0.00001632395,0.9659551,0.02314963,0.005766512,0.004592801,0.00001267155],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09468523,0.00111558,0.888513,0.0007144125,0.0001455673,0.00008742123,0.0002226169,0.003399442,0.01111669],"genre_scores_gemma":[0.6571176,0.0006230049,0.3368801,0.0002782478,0.00004857842,0.0001094639,0.0003538369,0.0001141384,0.004475032],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003783157,"threshold_uncertainty_score":0.007522285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0798020758351624,"score_gpt":0.3590371034644526,"score_spread":0.2792350276292901,"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."}}