{"id":"W4406016680","doi":"10.1038/s41467-024-55321-8","title":"TOPS-speed complex-valued convolutional accelerator for feature extraction and inference","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Neural Networks and Reservoir Computing","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"State Key Laboratory of Information Photonics and Optical Communications; Beijing University of Posts and Telecommunications; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Synthetic aperture radar; Convolutional neural network; Artificial intelligence; Deep learning; Feature extraction; Neuromorphic engineering; Artificial neural network; Inference; Computer hardware; Pattern recognition (psychology); Computer architecture; Computer engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002926836,0.0003064133,0.0001715333,0.0002584116,0.0002009327,0.0005244846,0.000871005,0.0002951656,0.009499581],"category_scores_gemma":[0.0008044821,0.0001570619,0.0001418457,0.0003724468,0.0002048365,0.0007344588,0.0003877934,0.0005522494,0.001380314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006841838,"about_ca_system_score_gemma":0.001092768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002457832,"about_ca_topic_score_gemma":0.004285316,"domain_scores_codex":[0.9998711,0.00001289088,0.000007880089,0.00001933235,0.00006692636,0.00002194026],"domain_scores_gemma":[0.9997523,0.0000690411,0.00002769175,0.00003801905,0.00009102144,0.00002194351],"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":[0.001377102,0.0004104227,0.004224198,0.0005543421,0.0001814335,0.0004772806,0.0002860334,0.09592902,0.2901323,0.05857597,0.03912131,0.5087306],"study_design_scores_gemma":[0.00004979698,0.0002217643,0.0007278144,0.00002355583,0.0000233033,0.0001891941,0.00003068664,0.8783043,0.09433994,0.005766597,0.02029532,0.00002779961],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.142494,0.0006502949,0.8234498,0.0007776779,0.0002572175,0.000172802,0.0008104834,0.01058245,0.02080533],"genre_scores_gemma":[0.7167266,0.0002670617,0.2663013,0.0002158899,0.00003223575,0.0001633811,0.0009022328,0.0001472984,0.01524396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009499581,"threshold_uncertainty_score":0.03177929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05151934142720608,"score_gpt":0.3699012503724737,"score_spread":0.3183819089452676,"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."}}