{"id":"W3091586704","doi":"10.1109/iscas45731.2020.9180548","title":"Towards Efficient On-Chip Learning using Equilibrium Propagation","year":2020,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Backpropagation; Pruning; Computation; Quantization (signal processing); Artificial neural network; Deep learning; Computer engineering; Field (mathematics); Chip; Artificial intelligence; Algorithm; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005382174,0.0005139031,0.0004955099,0.0003858947,0.000357565,0.0009881011,0.001571562,0.0006813779,0.003554417],"category_scores_gemma":[0.002144624,0.0002899601,0.0002393516,0.0005010291,0.0006537368,0.001424391,0.0008702513,0.001175515,0.0009737427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007707132,"about_ca_system_score_gemma":0.001155684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002727808,"about_ca_topic_score_gemma":0.005089642,"domain_scores_codex":[0.9995784,0.00009720738,0.00001687815,0.00005063973,0.0001957253,0.00006108737],"domain_scores_gemma":[0.99929,0.0003623444,0.00004326523,0.0001194256,0.0001602215,0.00002470723],"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":[0.0003414328,0.0002494524,0.001005228,0.0002657388,0.00007201653,0.0001606976,0.0001660351,0.3823023,0.05046528,0.1488482,0.006701223,0.4094224],"study_design_scores_gemma":[0.00001859205,0.00004203174,0.00006330517,0.000009772006,0.000007687124,0.00002685376,0.00001269799,0.9741818,0.01028412,0.01254287,0.00280412,0.000006109295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02196316,0.0003115668,0.9700004,0.0003099303,0.00006280855,0.00003833819,0.00002794309,0.001391777,0.005894095],"genre_scores_gemma":[0.5038078,0.0004482589,0.488109,0.0003018891,0.00005094902,0.0001041959,0.00009497576,0.0001643459,0.006918549],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003554417,"threshold_uncertainty_score":0.01189065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04793242669825894,"score_gpt":0.2702612013766075,"score_spread":0.2223287746783486,"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."}}