{"id":"W3034007088","doi":"10.3389/fnins.2021.633674","title":"Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias","year":2021,"lang":"en","type":"preprint","venue":"Frontiers in Neuroscience","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"Samsung; European Research Council; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Estimator; MNIST database; Computer science; Artificial neural network; Scaling; Backpropagation; Cross entropy; Deep learning; Algorithm; Artificial intelligence; Applied mathematics; Mathematics; Pattern recognition (psychology); Statistics","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":[0.001235545,0.001652498,0.0005899424,0.0007768317,0.0004183257,0.0009066957,0.001558635,0.001171377,0.003140275],"category_scores_gemma":[0.007190461,0.0004246512,0.0005176569,0.0004988449,0.0009449435,0.002067912,0.002275572,0.001974913,0.001412149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027462,"about_ca_system_score_gemma":0.001159753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004397283,"about_ca_topic_score_gemma":0.005475422,"domain_scores_codex":[0.9994279,0.0001152351,0.00003773612,0.000136876,0.000205178,0.0000770588],"domain_scores_gemma":[0.9986036,0.0005463862,0.0001141459,0.0002768761,0.000385986,0.0000730644],"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":[0.0003600846,0.00027937,0.00225593,0.0002242681,0.0001109444,0.0003203969,0.0002236297,0.5071264,0.04597995,0.05698645,0.009036534,0.377096],"study_design_scores_gemma":[0.00001672685,0.00005166157,0.0001574113,0.00001107823,0.0000101963,0.00003786311,0.000007537016,0.9779991,0.009475973,0.01058495,0.001637731,0.00000989404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05308855,0.0004840064,0.9356649,0.0004975692,0.0002213902,0.00006728802,0.0000988932,0.004745572,0.005131863],"genre_scores_gemma":[0.6729566,0.0004087668,0.3188444,0.0005087055,0.000173928,0.0001598571,0.0003700491,0.001034369,0.00554326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004397283,"threshold_uncertainty_score":0.01050526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03290051895411088,"score_gpt":0.2678406362161545,"score_spread":0.2349401172620436,"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."}}