{"id":"W2954143905","doi":"10.1103/physrevresearch.1.033030","title":"Takens-inspired neuromorphic processor: A downsizing tool for random recurrent neural networks via feature extraction","year":2019,"lang":"en","type":"article","venue":"Physical Review Research","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Neuromorphic engineering; Recurrent neural network; Artificial neural network; Set (abstract data type); Feature (linguistics); Feature extraction; Pattern recognition (psychology)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006646502,0.0002260828,0.0004909097,0.00005687038,0.0001660878,0.00005180388,0.0002436369,0.0000526005,0.00001446708],"category_scores_gemma":[0.0003647635,0.0001885566,0.0002092589,0.0005709124,0.00003448271,0.0002926888,0.00006653167,0.001142693,0.00005555454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000660279,"about_ca_system_score_gemma":0.00001518964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.87768e-7,"about_ca_topic_score_gemma":5.695866e-7,"domain_scores_codex":[0.9980679,0.0001835684,0.0002603814,0.0004038507,0.0004259372,0.000658425],"domain_scores_gemma":[0.9983614,0.0009433592,0.00005408089,0.0003268502,0.0001944907,0.0001197873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005253589,0.0002077298,0.00006718675,0.01656235,0.00006568364,0.00002850096,0.00009919763,0.09385969,0.1527699,0.0002884207,0.005221368,0.7303047],"study_design_scores_gemma":[0.0009665887,0.0002413949,0.0001359111,0.001738608,0.00003182838,0.0000217262,0.000003739838,0.9731785,0.003918619,0.0003759237,0.01906886,0.0003183004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8850938,0.07652065,0.02522646,0.00132665,0.001521834,0.008858921,0.00001480742,0.0007937776,0.0006430888],"genre_scores_gemma":[0.9939948,0.004597744,0.000133397,0.0001294739,0.0007114091,0.0002654711,0.00002504944,0.00005744327,0.00008522199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8793188,"threshold_uncertainty_score":0.7689113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0730995200511021,"score_gpt":0.3815461642864464,"score_spread":0.3084466442353443,"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."}}