{"id":"W2806498722","doi":"10.1007/s12021-019-09424-z","title":"NengoDL: Combining Deep Learning and Neuromorphic Modelling Methods","year":2019,"lang":"en","type":"preprint","venue":"Neuroinformatics","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Blackberry (Canada)","funders":"Office of Naval Research","keywords":"Computer science; Benchmarking; Neuromorphic engineering; Artificial intelligence; Construct (python library); Deep learning; Convolutional neural network; Key (lock); Machine learning; Artificial neural network; Software; Programming language","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0003255815,0.0004640932,0.0005617894,0.0001715023,0.0001592312,0.00016731,0.0002656133,0.0002382863,0.000006585985],"category_scores_gemma":[0.000094537,0.0005146088,0.0001048333,0.0001229505,0.00003757041,0.0002708125,0.0006698238,0.002666212,0.00002577079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003063192,"about_ca_system_score_gemma":0.00001680183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.536351e-7,"about_ca_topic_score_gemma":1.549017e-7,"domain_scores_codex":[0.9983243,0.0001019553,0.0006595373,0.0002682001,0.0001992851,0.0004467174],"domain_scores_gemma":[0.9987223,0.0005093255,0.0002098668,0.0003806992,0.00004396241,0.0001339173],"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":[0.000003593553,0.00000286012,0.00002906422,0.001053855,0.00001728273,0.000008403198,0.0008180435,0.9812015,0.0004911476,0.0000705799,0.00001000108,0.01629365],"study_design_scores_gemma":[0.0002087228,0.00004567362,0.00001461529,0.0001881169,0.0000393112,0.00007268065,0.0001015324,0.994505,0.001158519,0.0005548074,0.002665491,0.0004455223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2669311,0.0006600289,0.7259438,0.00001319698,0.00152434,0.0003340791,0.000002899504,0.0009038125,0.003686747],"genre_scores_gemma":[0.8656456,0.001634336,0.1320748,0.0001695426,0.0001546705,0.00001111008,0.00003745076,0.0001771797,0.00009530668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5987144,"threshold_uncertainty_score":0.9997305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04812619449195356,"score_gpt":0.2885476902886469,"score_spread":0.2404214957966933,"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."}}