{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005911815,0.00006561364,0.00006065026,0.00001676006,0.00009289519,0.0001095973,0.0002704494,0.00001821369,0.00001503814],"category_scores_gemma":[0.00001523309,0.0000529039,0.00002991669,0.0003392615,0.00001159006,0.00008219783,0.0001375266,0.0001082269,0.00007451807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000013382,"about_ca_system_score_gemma":0.00002595003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005627395,"about_ca_topic_score_gemma":1.303061e-7,"domain_scores_codex":[0.9993369,0.00002455901,0.0001023406,0.0002438742,0.0001531863,0.0001391429],"domain_scores_gemma":[0.9996913,0.00002075168,0.00003814066,0.0001402362,0.00002652328,0.00008306648],"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":[0.000004543217,0.0000412763,0.00007456537,0.0000090547,0.000004155524,0.000003504731,0.000356803,0.7811565,0.03945861,0.1413407,0.0005431543,0.03700712],"study_design_scores_gemma":[0.00006312556,0.00005432703,0.0001287153,0.000004758285,0.000001253983,0.00000159841,0.000007460322,0.9886751,0.009388539,0.000156553,0.001446003,0.00007261665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1758537,0.000007770254,0.8121048,0.006606046,0.00005743856,0.0001286857,1.480959e-7,0.0002355555,0.005005841],"genre_scores_gemma":[0.9832795,5.11402e-7,0.01527605,0.001236935,0.0001206468,0.000004893866,8.567511e-7,0.000004912571,0.00007571295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8074257,"threshold_uncertainty_score":0.2157358,"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."}}