{"id":"W4399986752","doi":"10.48550/arxiv.2406.14723","title":"Online Training of Hopfield Networks using Predictive Coding","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Predictive coding; Computer science; Coding (social sciences); Hopfield network; Artificial intelligence; Training (meteorology); Machine learning; Artificial neural network; Mathematics; Statistics; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009981095,0.001081022,0.0008357128,0.0006076327,0.0005096607,0.0008913237,0.001641097,0.00136478,0.003249088],"category_scores_gemma":[0.005569983,0.0006981698,0.0004768683,0.0004524137,0.000786407,0.001179129,0.0009291596,0.001473742,0.0004249332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001408266,"about_ca_system_score_gemma":0.001470612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02304902,"about_ca_topic_score_gemma":0.02269171,"domain_scores_codex":[0.9996847,0.00005883459,0.0000244795,0.00008284436,0.00008571574,0.00006353558],"domain_scores_gemma":[0.9981957,0.00116311,0.0001250685,0.0001217264,0.0003233228,0.00007114744],"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":[0.00007060131,0.00004386784,0.0006733719,0.00004798067,0.00002555094,0.00005136771,0.00005268012,0.9290287,0.00133326,0.002661231,0.0006445041,0.0653669],"study_design_scores_gemma":[0.000003727174,0.000007997748,0.0000269357,0.00000300968,0.000001825091,0.000002391936,0.000001742665,0.999014,0.0002176851,0.0006611497,0.00005791506,0.000001484877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1362668,0.00108253,0.8482246,0.0004818267,0.0001644513,0.0001501057,0.0001416127,0.002650787,0.01083723],"genre_scores_gemma":[0.9036643,0.0002001189,0.09281038,0.000181154,0.00003664416,0.0001321524,0.0002111056,0.00007800494,0.002686277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02304902,"threshold_uncertainty_score":0.04582971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1436465073991262,"score_gpt":0.2202220965371843,"score_spread":0.07657558913805809,"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."}}