{"id":"W4400416862","doi":"10.1364/optica.523225","title":"Control-free and efficient integrated photonic neural networks via hardware-aware training and pruning","year":2024,"lang":"en","type":"article","venue":"Optica","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Innovation and Technology Fund; Chinese University of Hong Kong; Shun Hing Institute of Advanced Engineering; University Grants Committee","keywords":"Computer science; Artificial neural network; Efficient energy use; Energy consumption; Computer hardware; Electronic engineering; Embedded system; Artificial intelligence; Engineering; Electrical engineering","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":[0.0003158051,0.000203217,0.0002384653,0.00008248848,0.0002463148,0.0007806766,0.0004583489,0.00007664649,0.000005081945],"category_scores_gemma":[0.00002960924,0.0001556063,0.00005337122,0.0003828262,0.00009491762,0.0001827416,0.0004755801,0.0004183417,0.000001825658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002151619,"about_ca_system_score_gemma":0.00003351563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001765856,"about_ca_topic_score_gemma":0.000005293224,"domain_scores_codex":[0.9985294,0.00006871275,0.0002243851,0.0005392074,0.0001714187,0.0004668778],"domain_scores_gemma":[0.9990953,0.0003106123,0.00003888103,0.0003405326,0.00004283228,0.0001718313],"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":[0.00003343732,0.00004926683,0.0002352301,0.0001416468,0.0001499813,0.0008077216,0.002173217,0.5408702,0.001217869,0.01594237,0.0007860538,0.437593],"study_design_scores_gemma":[0.0003343527,0.0001024063,0.0001757809,0.0001740968,0.00001508909,0.0001423913,0.00003850668,0.9977005,0.00002174012,0.0001701028,0.0009350418,0.0001900639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1585368,0.004182905,0.8338462,0.001631814,0.0008478572,0.0002337262,0.000002124871,0.0004092024,0.0003093482],"genre_scores_gemma":[0.9931706,0.00003628845,0.006339154,0.0002278584,0.0001483726,0.000007819278,0.000001749573,0.00001854561,0.00004961402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8346338,"threshold_uncertainty_score":0.7528083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01103642808667571,"score_gpt":0.2201113042816212,"score_spread":0.2090748761949455,"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."}}