{"id":"W2611142117","doi":"10.3389/fninf.2017.00033","title":"Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator","year":2017,"lang":"en","type":"article","venue":"Frontiers in Neuroinformatics","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation; Air Force Office of Scientific Research; Ontario Innovation Trust","keywords":"Computer science; Python (programming language); Implementation; Computation; Software; Artificial neural network; Parallel computing; Computer architecture simulator; Graph; Algorithm; Artificial intelligence; Operating system; Programming language; Theoretical computer science","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":[0.0003947527,0.0008181156,0.0004201729,0.0004058445,0.0004357128,0.0007814725,0.001361425,0.0006207766,0.008547684],"category_scores_gemma":[0.003250475,0.0004386429,0.0005807193,0.0003888999,0.0004794388,0.0009486869,0.0008971491,0.001112357,0.001385598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001096411,"about_ca_system_score_gemma":0.002087179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008054811,"about_ca_topic_score_gemma":0.01409637,"domain_scores_codex":[0.9997608,0.00005202771,0.00001250944,0.00004329106,0.00007550707,0.0000558343],"domain_scores_gemma":[0.999171,0.0004946855,0.00003660778,0.0001029905,0.00014284,0.00005199394],"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":[0.0004625098,0.0001732814,0.004835911,0.0003345739,0.00008963021,0.000250117,0.0002877136,0.7986998,0.02173202,0.03284213,0.02029425,0.1199982],"study_design_scores_gemma":[0.00003838903,0.00001491894,0.0003345355,0.00001055791,0.00001105555,0.00002156029,0.00002914907,0.9815107,0.005053381,0.008407836,0.004557564,0.00001039073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1416303,0.0002736024,0.8046713,0.0007657773,0.0002159279,0.0002041755,0.001255811,0.0273788,0.02360416],"genre_scores_gemma":[0.48439,0.0002145986,0.4989704,0.0003507203,0.00002606296,0.0006151224,0.00210375,0.005383445,0.007945937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008547684,"threshold_uncertainty_score":0.02859491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01174801558265674,"score_gpt":0.2272998048623416,"score_spread":0.2155517892796849,"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."}}